© 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. 15-LLAMASCOPE-RES-131K
    11. 86660
    Prev
    Next
    INDEX
    Explanations

    ellipses or pauses in written 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
     Point
    -0.06
    dec
    -0.06
    point
    -0.06
    latin
    -0.06
    Crime
    -0.05
     struct
    -0.05
     symbol
    -0.05
    -0.05
    BM
    -0.05
    ..
    -0.05
    POSITIVE LOGITS
    -eslint
    0.08
    ós
    0.08
    Ľ
    0.08
    leck
    0.07
    _CONTINUE
    0.07
    .CustomButton
    0.07
    gili
    0.07
    BorderStyle
    0.07
    uden
    0.07
     بÙĪابة
    0.07
    Activations Density 0.039%

    No Known Activations