© 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. 93859
    Prev
    Next
    INDEX
    Explanations

    references to the Express web framework and its components

    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
    ately
    -0.07
     Abrams
    -0.06
    annya
    -0.06
    ulet
    -0.06
     gros
    -0.06
    775
    -0.06
    orta
    -0.06
    ftime
    -0.06
    crets
    -0.06
     subjective
    -0.06
    POSITIVE LOGITS
    iers
    0.07
    mini
    0.07
    INGTON
    0.07
    ington
    0.06
    icana
    0.06
     Gord
    0.06
    apl
    0.06
    管
    0.06
    apr
    0.06
    ÙĪÙĩ
    0.06
    Activations Density 0.000%

    No Known Activations