© 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. 18289
    Prev
    Next
    INDEX
    Explanations

    punctuation and symbols associated with data presentation or formatting

    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
    arel
    -0.07
    zon
    -0.07
    инкÑĥ
    -0.07
    INES
    -0.07
    инок
    -0.07
    AREN
    -0.07
    zier
    -0.06
    mazon
    -0.06
    dong
    -0.06
    outil
    -0.06
    POSITIVE LOGITS
    breadcrumbs
    0.06
    ëł´
    0.06
     traction
    0.06
    ©
    0.06
     ders
    0.06
    suppress
    0.06
    UNUSED
    0.06
    (Bundle
    0.06
    ê·¹
    0.06
     пÑĢиб
    0.06
    Activations Density 0.009%

    No Known Activations