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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 77322
    Prev
    Next
    INDEX
    Explanations

    attribution phrases indicating the source or credit for information or content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zin
    -0.07
    ras
    -0.07
    loor
    -0.07
    wie
    -0.06
    athon
    -0.06
    ps
    -0.06
    nc
    -0.06
    stat
    -0.06
    NC
    -0.06
    aver
    -0.06
    POSITIVE LOGITS
    ously
    0.09
    ably
    0.08
    clide
    0.08
    ately
    0.08
    页éĿ¢åŃĺæ¡£å¤ĩ份
    0.08
    tesy
    0.07
    prisingly
    0.07
    ettel
    0.07
    à¸Ńà¸ĩà¸Īาà¸ģ
    0.07
     of
    0.07
    Activations Density 0.004%

    No Known Activations