© 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 EvalsExportsinterp-engineNEWAPI 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. 54444
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "named" or variations indicating identification

    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
    _ASSUME
    -0.09
    entin
    -0.09
    iyan
    -0.08
    _Tis
    -0.08
    Hints
    -0.08
    ôi
    -0.08
    áš
    -0.07
    emey
    -0.07
    brook
    -0.07
    /WebAPI
    -0.07
    POSITIVE LOGITS
     whose
    0.08
    unset
    0.07
    whose
    0.07
     who
    0.07
     whom
    0.06
     p
    0.06
    inking
    0.06
    thesis
    0.06
    who
    0.06
    ãģ¿
    0.06
    Activations Density 0.006%

    No Known Activations