© 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. 91891
    Prev
    Next
    INDEX
    Explanations

    references to prestigious publications 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
    oulos
    -0.07
    omik
    -0.07
    loquent
    -0.06
     INTERVAL
    -0.06
    ileo
    -0.06
    CENTER
    -0.06
    urat
    -0.06
    wend
    -0.06
    ezier
    -0.06
    undler
    -0.06
    POSITIVE LOGITS
    oment
    0.07
    uisse
    0.07
    æ²»
    0.07
    олод
    0.06
    dorf
    0.06
    cko
    0.06
    enti
    0.06
    .gov
    0.06
    Initialized
    0.06
    TabControl
    0.06
    Activations Density 0.001%

    No Known Activations