© 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. 87453
    Prev
    Next
    INDEX
    Explanations

    Alphanumeric sequences, likely referencing codes or identifiers

    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
    reds
    -0.08
    orne
    -0.07
    ilight
    -0.07
    chten
    -0.07
    егÑĢа
    -0.07
    riad
    -0.07
    archs
    -0.07
    .lu
    -0.07
    ÄĻd
    -0.07
    ihat
    -0.06
    POSITIVE LOGITS
    veau
    0.06
     Bloc
    0.06
     Fruit
    0.06
    uhl
    0.06
     Duy
    0.06
     NSK
    0.06
     Morrow
    0.06
    \admin
    0.05
     Hamm
    0.05
    Ł
    0.05
    Activations Density 0.009%

    No Known Activations