© 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. 107916
    Prev
    Next
    INDEX
    Explanations

    post metadata and titles

    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
     Stam
    -0.07
    ο
    -0.07
    enos
    -0.06
    uze
    -0.06
    åij¢
    -0.06
    orce
    -0.06
    emer
    -0.06
    inen
    -0.06
    ania
    -0.06
    .lon
    -0.06
    POSITIVE LOGITS
    EMPLARY
    0.08
     exc
    0.07
    _exc
    0.07
    exc
    0.07
    ynn
    0.07
     Uncategorized
    0.07
    coins
    0.07
    acades
    0.06
    Exc
    0.06
     kra
    0.06
    Activations Density 0.004%

    No Known Activations