© 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. 75162
    Prev
    Next
    INDEX
    Explanations

    instances of emergency situations and the respective responses

    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
    isle
    -0.07
    isy
    -0.06
    ovan
    -0.06
    åĿĬ
    -0.06
     Petty
    -0.06
    REAT
    -0.06
    ierge
    -0.06
    ardin
    -0.06
    CI
    -0.06
     åĮ
    -0.06
    POSITIVE LOGITS
    aeda
    0.07
     viá»ĩn
    0.07
     schools
    0.07
     storage
    0.07
     Cent
    0.06
    stants
    0.06
     camp
    0.06
     facility
    0.06
     åĬ
    0.06
    .mvc
    0.06
    Activations Density 0.135%

    No Known Activations