© 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. 93736
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals involved in controversy or political drama

    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
    (çģ«
    -0.07
    ÄĽtÅ¡
    -0.07
     chặt
    -0.07
     stabbed
    -0.07
    ipy
    -0.07
    _timestamp
    -0.07
    .sms
    -0.07
     sta
    -0.06
    ivel
    -0.06
    ictionary
    -0.06
    POSITIVE LOGITS
    iaux
    0.09
     serial
    0.07
     Applied
    0.06
     fur
    0.06
     Vul
    0.06
    als
    0.06
    marsh
    0.06
     Bed
    0.06
     bed
    0.06
    bed
    0.06
    Activations Density 0.003%

    No Known Activations