© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 129023
    Prev
    Next
    INDEX
    Explanations

    negative indicators or ratings

    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
    .land
    -0.07
    sek
    -0.07
    agara
    -0.06
    483
    -0.06
    esc
    -0.06
     Flo
    -0.06
    agne
    -0.06
    ç«Ļ
    -0.06
    iska
    -0.06
    subtotal
    -0.06
    POSITIVE LOGITS
    :\"
    0.07
    ucht
    0.06
    жÑĥ
    0.06
    licht
    0.06
    lew
    0.06
    ursal
    0.06
     Gesch
    0.06
    _cre
    0.06
    ording
    0.06
     Marl
    0.06
    Activations Density 0.001%

    No Known Activations