© 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. 23243
    Prev
    Next
    INDEX
    Explanations

    repeated phrases indicating small adjustments or specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    itra
    -0.15
    ãģ°ãģĭãĤĬ
    -0.14
    .ba
    -0.14
    ãĥ¼ãĥĢ
    -0.14
    loth
    -0.13
    itus
    -0.13
    iomanip
    -0.13
    asco
    -0.13
    ÑĢами
    -0.13
     hvad
    -0.12
    POSITIVE LOGITS
     slight
    0.32
     briefly
    0.30
     slightly
    0.29
     occasionally
    0.27
     small
    0.26
    brief
    0.26
    Brief
    0.24
     tiny
    0.24
    small
    0.23
     minor
    0.23
    Activations Density 0.003%

    No Known Activations