© 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 EvalsExportsinterp-engineNEWAPI 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. 95189
    Prev
    Next
    INDEX
    Explanations

    relevant numerical data or references related to scientific or technical measurements

    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
    urope
    -0.08
    strap
    -0.06
    weeney
    -0.06
     Bes
    -0.06
    ÑĤон
    -0.06
     Jenner
    -0.06
    @student
    -0.06
    onse
    -0.06
     Mun
    -0.06
    amarin
    -0.06
    POSITIVE LOGITS
    å¹´
    0.08
    Ñģклад
    0.08
    Subset
    0.07
    sher
    0.07
     yılı
    0.07
    DITION
    0.07
    /svg
    0.06
    acey
    0.06
    Äı
    0.06
    oki
    0.06
    Activations Density 0.100%

    No Known Activations