© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 18-LLAMASCOPE-RES-32K
    11. 12368
    Prev
    Next
    INDEX
    Explanations

    specific names and titles related to individuals, organizations, and locations in news articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the special beginning-of-text marker indicating the start of a document or segment

    oai_token-act-pair · gpt-5Triggered by @jamesnaruto04

    text beginnings

    np_max-act · claude-4-5-sonnetTriggered by @jamesnaruto04
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .gameserver
    -0.13
    âĦĸâĦĸ
    -0.12
    .UnitTesting
    -0.12
    ROTO
    -0.12
    _Tis
    -0.12
    ä¹İ
    -0.12
    agua
    -0.12
    usher
    -0.11
    -urlencoded
    -0.11
     authDomain
    -0.10
    POSITIVE LOGITS
    iš
    0.11
    _Desc
    0.11
    á»ijn
    0.10
    ाद
    0.10
    PropertyValue
    0.10
     ¦
    0.10
    ãĤĦãĤĭ
    0.10
     маÑĤи
    0.10
    Æ°ng
    0.10
    اب
    0.10
    Activations Density 1.164%

    No Known Activations