© 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. 106259
    Prev
    Next
    INDEX
    Explanations

    elements related to CSS styling and 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
    eken
    -0.07
    inker
    -0.07
    egal
    -0.07
    Compat
    -0.06
    emo
    -0.06
    fal
    -0.06
    xiety
    -0.06
    edii
    -0.06
    atten
    -0.06
    apas
    -0.06
    POSITIVE LOGITS
    _lineno
    0.10
    ritz
    0.07
    ör
    0.07
    ãģ¾ãģ¾
    0.07
    (Spring
    0.06
     Sesso
    0.06
    ILINE
    0.06
     Campo
    0.06
    BLOCK
    0.06
     Liberation
    0.06
    Activations Density 0.013%

    No Known Activations