© 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. 29016
    Prev
    Next
    INDEX
    Explanations

    references to rewrite rules and their applications in optimization contexts

    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
    arella
    -0.07
    inka
    -0.06
    ropoda
    -0.06
    ιÏĥÏĦή
    -0.06
    ırak
    -0.06
     Incre
    -0.06
    eron
    -0.06
    outs
    -0.06
     Bomb
    -0.06
    ander
    -0.06
    POSITIVE LOGITS
     nor
    0.07
    strup
    0.06
     Lim
    0.06
     feast
    0.06
    .AP
    0.06
    ละ
    0.06
    .lp
    0.06
    atism
    0.06
    že
    0.06
    inan
    0.06
    Activations Density 0.001%

    No Known Activations