© 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. 84299
    Prev
    Next
    INDEX
    Explanations

    phrases indicating initial reactions or responses to various events or actions

    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
    gota
    -0.07
    celik
    -0.06
    emek
    -0.06
    cek
    -0.06
    campo
    -0.06
    ationship
    -0.06
    icari
    -0.06
    اسÙħ
    -0.06
    ftware
    -0.06
    terdam
    -0.06
    POSITIVE LOGITS
    aph
    0.07
    own
    0.07
    ->{'
    0.07
    mixed
    0.07
    bage
    0.07
    rement
    0.06
    ź
    0.06
    gre
    0.06
     vol
    0.06
    zen
    0.06
    Activations Density 0.006%

    No Known Activations