© 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. 62827
    Prev
    Next
    INDEX
    Explanations

    key performance indicators and trends in the market

    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
    atchet
    -0.07
    uide
    -0.06
    onyms
    -0.06
     DVDs
    -0.06
    afür
    -0.06
    amber
    -0.06
    itta
    -0.06
    Äįas
    -0.06
    .opend
    -0.06
    å¦
    -0.06
    POSITIVE LOGITS
     growth
    0.09
     Trends
    0.07
     trends
    0.07
    è¶
    0.07
     Growth
    0.07
     trend
    0.07
    growth
    0.07
    æĬ¥åijĬ
    0.07
    _growth
    0.07
    USAGE
    0.07
    Activations Density 0.009%

    No Known Activations