© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 16-LLAMASCOPE-RES-32K
    6. 918
    Prev
    Next
    INDEX
    Explanations

    words and phrases that denote relationships and connections between ideas or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etter
    -0.14
    iev
    -0.14
    ĶåĽŀ
    -0.14
    rell
    -0.13
    apl
    -0.13
    ader
    -0.13
    ishops
    -0.13
    etti
    -0.13
    ucks
    -0.12
    issent
    -0.12
    POSITIVE LOGITS
    PerPixel
    0.13
    #ac
    0.13
    oola
    0.12
    ãĤ¤ãĤ¯
    0.12
     âĵĺ
    0.12
     bas
    0.12
    emek
    0.12
    Vectorizer
    0.12
    ntax
    0.12
     bag
    0.12
    Activations Density 0.158%

    No Known Activations