© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 62009
    Prev
    Next
    INDEX
    Explanations

    question marks indicating inquiries or questions

    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
    avis
    -0.08
    å±¥
    -0.07
    lyn
    -0.07
     Masc
    -0.06
    ãģªãĤī
    -0.06
     ç²
    -0.06
    ÑĤик
    -0.06
    浪
    -0.06
    TypeInfo
    -0.06
    sez
    -0.06
    POSITIVE LOGITS
     answer
    0.09
     Answer
    0.09
     ANSW
    0.08
    Answer
    0.07
    Ans
    0.07
    :
    0.07
     Ans
    0.07
    answer
    0.06
     answers
    0.06
     answered
    0.06
    Activations Density 0.021%

    No Known Activations