© 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. 81047
    Prev
    Next
    INDEX
    Explanations

    copyright symbols and function declarations

    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
    Accessor
    -0.07
    esor
    -0.06
    út
    -0.06
    onica
    -0.06
     Voy
    -0.06
    mada
    -0.06
    .contentSize
    -0.06
     Constant
    -0.06
    526
    -0.06
    abyrinth
    -0.06
    POSITIVE LOGITS
    eer
    0.06
     Lon
    0.06
    919
    0.06
    angu
    0.06
    tha
    0.06
    ÑģÑĤÑĢо
    0.06
    atie
    0.06
    Ñīий
    0.06
    yh
    0.06
    swick
    0.06
    Activations Density 0.001%

    No Known Activations