© 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. 91990
    Prev
    Next
    INDEX
    Explanations

    references to academic departments and institutions

    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
    ield
    -0.07
    aze
    -0.07
    اÙĨا
    -0.06
    азв
    -0.06
     anything
    -0.06
    èİ
    -0.06
    apest
    -0.06
    ason
    -0.06
    Ñķ
    -0.06
    AspNet
    -0.06
    POSITIVE LOGITS
    uste
    0.07
    ONA
    0.06
    -Sah
    0.06
     nucleus
    0.06
    ADDE
    0.06
    964
    0.06
    ignet
    0.06
    896
    0.06
    Æ°á»Łng
    0.06
    ãĥ¥
    0.06
    Activations Density 0.007%

    No Known Activations