© 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. 79709
    Prev
    Next
    INDEX
    Explanations

    guidance on personal organization and prioritization

    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
    olics
    -0.07
     kodu
    -0.07
    /wiki
    -0.07
    zion
    -0.07
     IQ
    -0.07
    ünst
    -0.07
    /Web
    -0.06
    lector
    -0.06
    iram
    -0.06
    weis
    -0.06
    POSITIVE LOGITS
     list
    0.07
     yourselves
    0.07
     yourself
    0.06
     ÑģпиÑģок
    0.06
     pen
    0.06
    (hr
    0.06
     your
    0.06
    408
    0.06
     liá»ĩt
    0.06
     Worksheet
    0.06
    Activations Density 0.009%

    No Known Activations