© 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. 84369
    Prev
    Next
    INDEX
    Explanations

    references to the market and its products

    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
    amin
    -0.07
     saja
    -0.06
    wap
    -0.06
    ¤íĶĦ
    -0.06
    inheritDoc
    -0.06
    raison
    -0.06
    usto
    -0.05
    опÑĢи
    -0.05
     Rol
    -0.05
    elia
    -0.05
    POSITIVE LOGITS
    jourd
    0.09
    today
    0.08
     today
    0.08
    wert
    0.08
    lal
    0.07
    oso
    0.07
    osal
    0.07
    errupted
    0.07
    icolon
    0.07
     brands
    0.07
    Activations Density 0.008%

    No Known Activations