© 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. 73016
    Prev
    Next
    INDEX
    Explanations

    references to educational programs and courses

    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
     sticky
    -0.07
    ãģ£ãģ¡
    -0.06
    oogle
    -0.06
    kinson
    -0.06
    kers
    -0.06
    ISIBLE
    -0.06
    elson
    -0.06
    aku
    -0.06
    ker
    -0.06
    adla
    -0.06
    POSITIVE LOGITS
    Lorem
    0.07
     cryst
    0.07
    _DM
    0.07
    tearDown
    0.07
     buffered
    0.07
    ỳ
    0.07
    afx
    0.06
     vô
    0.06
    виÑĩ
    0.06
    arts
    0.06
    Activations Density 0.010%

    No Known Activations