© 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. 81393
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly commas

    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
    urch
    -0.08
    tbl
    -0.07
    شت
    -0.06
    utan
    -0.06
    ÏĥÏīÏĢ
    -0.06
    uggy
    -0.06
     behalf
    -0.05
    éĻ½
    -0.05
     dad
    -0.05
    è¡
    -0.05
    POSITIVE LOGITS
    mise
    0.07
    wij
    0.07
    emand
    0.07
    WSC
    0.07
    elsen
    0.07
    га
    0.07
    #{
    0.07
    ospace
    0.06
     Kra
    0.06
     ä½IJ
    0.06
    Activations Density 0.007%

    No Known Activations