© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 96950
    Prev
    Next
    INDEX
    Explanations

    positive adjectives describing ability or potential

    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
    endregion
    -0.07
    inality
    -0.07
    gue
    -0.07
    atsu
    -0.07
    lung
    -0.07
    endforeach
    -0.07
    suz
    -0.07
    ská
    -0.07
    visibility
    -0.06
    bourg
    -0.06
    POSITIVE LOGITS
    ãĥŃãĥ¼
    0.07
    OfYear
    0.06
     Gott
    0.06
     Traits
    0.06
    енка
    0.06
     instability
    0.06
    ÌĢ
    0.06
     Bond
    0.06
    _micro
    0.06
    μμ
    0.06
    Activations Density 0.000%

    No Known Activations