© 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. 125285
    Prev
    Next
    INDEX
    Explanations

    references to legal terms and community supervision concepts

    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
     DAMAGES
    -0.08
    889
    -0.08
    ogg
    -0.08
    ecast
    -0.07
    phy
    -0.07
    izzo
    -0.07
    oga
    -0.07
    ebo
    -0.07
    ULL
    -0.07
    ully
    -0.07
    POSITIVE LOGITS
     urine
    0.07
     reporting
    0.06
     supervision
    0.06
     monitoring
    0.06
    ainers
    0.06
     parole
    0.06
     probation
    0.06
     ank
    0.06
     monitors
    0.06
     tail
    0.06
    Activations Density 0.007%

    No Known Activations