© 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. 126839
    Prev
    Next
    INDEX
    Explanations

    descriptors of governance and societal structures

    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
    ileo
    -0.07
    vier
    -0.07
    ifestyles
    -0.07
    vou
    -0.07
    ucid
    -0.07
    eya
    -0.07
     Anatomy
    -0.07
    ModelState
    -0.06
    hai
    -0.06
    ffc
    -0.06
    POSITIVE LOGITS
    stre
    0.06
    961
    0.06
    еÑģÑĮ
    0.06
     residents
    0.06
    cron
    0.06
     cuenta
    0.06
     frank
    0.06
     inhabitants
    0.05
    Ïģοι
    0.05
     Vand
    0.05
    Activations Density 0.004%

    No Known Activations