© 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. 126713
    Prev
    Next
    INDEX
    Explanations

    formatting and citation styles in documents

    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
     Dit
    -0.07
    acman
    -0.06
     Transcript
    -0.06
    rovers
    -0.06
    лÑĭÑħ
    -0.06
    оÑĤа
    -0.06
    \helpers
    -0.06
    vro
    -0.06
    iddy
    -0.06
    cies
    -0.06
    POSITIVE LOGITS
    ï½į
    0.06
    .toolbox
    0.06
    623
    0.06
    emez
    0.06
    alg
    0.06
    igen
    0.06
     stil
    0.06
    utura
    0.06
     inf
    0.06
    BOOLEAN
    0.06
    Activations Density 0.007%

    No Known Activations