© 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. 127776
    Prev
    Next
    INDEX
    Explanations

    references to a competitive event or contest

    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
    altar
    -0.08
    \Schema
    -0.07
    аÑĢан
    -0.07
    ç«ĭãģ¡
    -0.07
    glas
    -0.07
    lastic
    -0.07
    DBObject
    -0.07
    å»Ĭ
    -0.07
    Ľå»º
    -0.07
    bulan
    -0.07
    POSITIVE LOGITS
     riding
    0.10
     riders
    0.09
     ride
    0.09
     rider
    0.09
     horse
    0.09
     stable
    0.08
     rides
    0.08
     saddle
    0.08
     horses
    0.08
     dress
    0.07
    Activations Density 0.002%

    No Known Activations