© 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. 87293
    Prev
    Next
    INDEX
    Explanations

    expressions of capability or possibility

    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
    inki
    -0.07
    .Dispatcher
    -0.07
    Bomb
    -0.07
    bomb
    -0.07
    QUEST
    -0.06
    .PropTypes
    -0.06
    agina
    -0.06
    åĬ¨
    -0.06
    _ABC
    -0.06
     QUEST
    -0.06
    POSITIVE LOGITS
    osta
    0.07
    rupt
    0.07
     Thomson
    0.06
    reta
    0.06
    iji
    0.06
     Easily
    0.06
    ɵ
    0.06
    asily
    0.06
     easily
    0.06
    907
    0.06
    Activations Density 0.023%

    No Known Activations