© 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. 55039
    Prev
    Next
    INDEX
    Explanations

    references to historical correspondence or communication

    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
     motions
    -0.07
     subt
    -0.06
    cht
    -0.06
    -www
    -0.06
    ahat
    -0.06
    gos
    -0.06
    ottes
    -0.06
    ENTE
    -0.06
    233
    -0.06
    bÃŃ
    -0.06
    POSITIVE LOGITS
     letter
    0.09
    letter
    0.08
     Letter
    0.08
     addressed
    0.08
     letters
    0.08
    -letter
    0.07
    Letter
    0.07
     LETTER
    0.07
    /license
    0.07
    _letter
    0.07
    Activations Density 0.014%

    No Known Activations