© 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. 75237
    Prev
    Next
    INDEX
    Explanations

    numerical data related to health outcomes

    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
    burgh
    -0.07
    iren
    -0.07
    scaled
    -0.07
     öden
    -0.06
    arena
    -0.06
     Tal
    -0.06
    orgia
    -0.06
     =============================================================================↵
    -0.06
     equ
    -0.06
    hol
    -0.06
    POSITIVE LOGITS
    eting
    0.08
    eldorf
    0.07
     Farms
    0.07
    .openg
    0.06
     пÑĢавил
    0.06
    _abort
    0.06
    createFrom
    0.06
    ¹Ħ
    0.06
    orate
    0.06
    Ñĥм
    0.06
    Activations Density 0.002%

    No Known Activations