© 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. 17-LLAMASCOPE-RES-131K
    11. 75065
    Prev
    Next
    INDEX
    Explanations

    specific terms related to official designations or authoritative classifications

    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
    ÃĹ↵↵
    -0.08
    ossal
    -0.07
     nonzero
    -0.07
     mennes
    -0.07
    stor
    -0.07
    Ậ
    -0.07
    ãĥŃãĥ¼
    -0.07
     ----------------------------------------------------------------------------↵
    -0.07
    åĭĻ
    -0.07
    зд
    -0.07
    POSITIVE LOGITS
     coverage
    0.06
     Banc
    0.06
     mod
    0.06
    .(
    0.05
    pton
    0.05
     Cummings
    0.05
    coverage
    0.05
     {?}
    0.05
    etta
    0.05
     dem
    0.05
    Activations Density 0.000%

    No Known Activations