© 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. 60881
    Prev
    Next
    INDEX
    Explanations

    references to adventure and exploration in a narrative context

    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
    cta
    -0.07
    posal
    -0.07
    èĬĿ
    -0.07
    ofday
    -0.07
     Madden
    -0.07
     audi
    -0.07
     î¡
    -0.07
    IRT
    -0.06
    baugh
    -0.06
     Audi
    -0.06
    POSITIVE LOGITS
     Gundam
    0.09
    ynes
    0.07
    unan
    0.07
    arth
    0.06
     tanks
    0.06
     Hamas
    0.06
     tank
    0.06
    æŃ
    0.06
     Episodes
    0.06
    swire
    0.06
    Activations Density 0.012%

    No Known Activations