© 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. 95814
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly commas in various contexts

    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
    vd
    -0.07
    yle
    -0.07
    aic
    -0.07
    âĢİ
    -0.07
    yst
    -0.07
    yun
    -0.07
    erek
    -0.06
    .ta
    -0.06
    ves
    -0.06
     Fairy
    -0.06
    POSITIVE LOGITS
    agas
    0.07
    unsch
    0.06
    abus
    0.06
    fort
    0.06
     Holt
    0.06
     же
    0.06
    DataContext
    0.06
     Geh
    0.06
     furthermore
    0.06
    _helpers
    0.06
    Activations Density 0.044%

    No Known Activations