© 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. 27224
    Prev
    Next
    INDEX
    Explanations

    punctuation and sentence structure within the text

    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
     note
    -0.07
    ãģªãģĬ
    -0.06
     puss
    -0.06
    jah
    -0.06
    -fontawesome
    -0.06
     remar
    -0.06
    note
    -0.06
     Note
    -0.06
    inger
    -0.05
    Note
    -0.05
    POSITIVE LOGITS
    [np
    0.08
    endor
    0.07
    irl
    0.07
    åľº
    0.07
    ØŃ
    0.07
    :animated
    0.07
    iew
    0.07
    eral
    0.06
    emu
    0.06
    .Done
    0.06
    Activations Density 0.053%

    No Known Activations