© 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. 119165
    Prev
    Next
    INDEX
    Explanations

    references to conflict and injuries in events

    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
    egal
    -0.07
    strup
    -0.07
    reta
    -0.07
     имÑĥ
    -0.07
     prostituer
    -0.07
    оÑĨÑĸ
    -0.07
    ForRow
    -0.06
    forman
    -0.06
    ngx
    -0.06
    Ñĥнд
    -0.06
    POSITIVE LOGITS
    ictured
    0.07
     i
    0.07
     h
    0.06
    0.06
     pictured
    0.06
     (
    0.06
     '
    0.06
    662
    0.06
     pic
    0.06
     blue
    0.06
    Activations Density 0.000%

    No Known Activations