© 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. 73316
    Prev
    Next
    INDEX
    Explanations

    structured data formats and logging messages

    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
    allet
    -0.06
    abeth
    -0.06
    رÙĪج
    -0.06
    .Month
    -0.06
     flashy
    -0.06
    ยาà¸Ļ
    -0.06
    mur
    -0.05
    ampus
    -0.05
     éĸĭ
    -0.05
    olan
    -0.05
    POSITIVE LOGITS
     NÄĽm
    0.07
     Anonymous
    0.06
    _HOOK
    0.06
    AIL
    0.06
    Anonymous
    0.06
    asca
    0.06
    ymph
    0.06
    ptal
    0.06
    Ñıви
    0.06
    072
    0.06
    Activations Density 0.023%

    No Known Activations