© 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 EvalsExportsAPI 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. 87402
    Prev
    Next
    INDEX
    Explanations

    terminology related to components and systems in computing

    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
    taire
    -0.07
    util
    -0.07
    /modal
    -0.07
    보기
    -0.07
    endoza
    -0.06
     Cush
    -0.06
    byn
    -0.06
     Nack
    -0.06
     tuto
    -0.06
    .ÎŁ
    -0.06
    POSITIVE LOGITS
     tens
    0.07
    ADDE
    0.07
     Timeline
    0.07
    ONGL
    0.07
    bang
    0.07
     unused
    0.06
    kle
    0.06
    .tell
    0.06
    MJ
    0.06
    CRET
    0.06
    Activations Density 0.001%

    No Known Activations