© 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. 69810
    Prev
    Next
    INDEX
    Explanations

    code-related elements, specifically drag-and-drop functionality

    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
    onta
    -0.07
    vent
    -0.07
     crowd
    -0.06
     hiding
    -0.06
     Peach
    -0.06
    301
    -0.06
    ople
    -0.05
     fart
    -0.05
     Pitt
    -0.05
     Ñĥв
    -0.05
    POSITIVE LOGITS
    _transfer
    0.08
    _TRANSFER
    0.08
    Transfer
    0.08
     Transfer
    0.07
    .transfer
    0.07
    .Transfer
    0.07
    /rfc
    0.07
    .Uri
    0.07
    .URI
    0.07
    TRANSFER
    0.07
    Activations Density 0.015%

    No Known Activations