© 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. 73757
    Prev
    Next
    INDEX
    Explanations

    negations and statements about what is not provided, accepted, or endorsed

    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
    allis
    -0.06
     обÑĢа
    -0.06
    óm
    -0.06
     werd
    -0.06
    епÑĤи
    -0.06
    raquo
    -0.06
    ĵ
    -0.06
    ëĿ
    -0.06
    krv
    -0.06
    alle
    -0.06
    POSITIVE LOGITS
     directly
    0.07
     currently
    0.07
    0.07
     paren
    0.06
    cdb
    0.06
    .generated
    0.06
    mia
    0.06
     accepting
    0.06
    edb
    0.06
    ẹ
    0.06
    Activations Density 0.012%

    No Known Activations