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

    Neuronpedia

    Jacobian LensNEW
    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. 17-LLAMASCOPE-RES-131K
    11. 85551
    Prev
    Next
    INDEX
    Explanations

    words associated with evaluation and scrutiny processes

    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
     merk
    -0.07
    à¥ĩय
    -0.07
    Adjacent
    -0.07
    qli
    -0.07
    uate
    -0.07
    ½Ķ
    -0.07
    quier
    -0.07
    oyal
    -0.07
    hear
    -0.07
    ç©´
    -0.07
    POSITIVE LOGITS
     whether
    0.09
     closely
    0.08
    æĺ¯åIJ¦
    0.07
     carefully
    0.07
     and
    0.07
     thoroughly
    0.06
     retrospect
    0.06
    whether
    0.06
     Klo
    0.06
    ç¯
    0.06
    Activations Density 0.033%

    No Known Activations