© 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. 87343
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals who have founded organizations, companies, or movements

    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
    atte
    -0.08
     huku
    -0.07
    Ñĥже
    -0.07
     defaultManager
    -0.07
    dn
    -0.07
    '])?
    -0.07
    orb
    -0.07
    æĿ¥èĩª
    -0.07
    crollView
    -0.07
    Suite
    -0.07
    POSITIVE LOGITS
     brand
    0.06
     Butter
    0.05
    Opens
    0.05
     upon
    0.05
     subsequent
    0.05
     club
    0.05
    agged
    0.05
     Seeds
    0.05
    end
    0.05
     Ltd
    0.05
    Activations Density 0.020%

    No Known Activations