© 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. 93898
    Prev
    Next
    INDEX
    Explanations

    specific measurements or quantities, particularly in relation to space and value

    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
    hip
    -0.07
     Lambert
    -0.07
    GenerationStrategy
    -0.07
     overall
    -0.06
    mdir
    -0.06
    zek
    -0.06
    referrer
    -0.06
    gregar
    -0.06
    eless
    -0.06
    uitka
    -0.06
    POSITIVE LOGITS
     of
    0.08
    ìĶ©
    0.07
     thereof
    0.07
    ãģĨãģ¡
    0.06
    pson
    0.06
    gia
    0.06
     của
    0.06
    /per
    0.06
    à¸Ĥà¸Ńà¸ĩ
    0.06
    ÑĢаÑĤно
    0.06
    Activations Density 0.010%

    No Known Activations