© 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. 117297
    Prev
    Next
    INDEX
    Explanations

    numerical dates and years related to legislation

    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
    hausen
    -0.08
    UTTON
    -0.07
    777
    -0.06
    ĵ°
    -0.06
    tape
    -0.06
    ogenesis
    -0.06
    tel
    -0.06
    WXYZ
    -0.06
    URRED
    -0.06
    837
    -0.06
    POSITIVE LOGITS
     Congress
    0.07
    HR
    0.06
    .nih
    0.06
     hearing
    0.06
    merce
    0.06
     Paulo
    0.06
    anki
    0.06
    OCR
    0.06
     bill
    0.06
    æģ¯
    0.06
    Activations Density 0.022%

    No Known Activations