© 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. 57267
    Prev
    Next
    INDEX
    Explanations

    terms related to legal and technical terminologies that signify critical issues or exceptions

    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
     Cow
    -0.06
     Cutter
    -0.06
     ostr
    -0.06
    egot
    -0.06
    068
    -0.06
    585
    -0.06
     emotion
    -0.06
     Kenn
    -0.06
     Coff
    -0.06
    iment
    -0.06
    POSITIVE LOGITS
    wizard
    0.07
    gov
    0.07
    ocos
    0.07
     Quartz
    0.06
    cente
    0.06
    ação
    0.06
    bah
    0.06
    org
    0.06
     Humb
    0.06
     policy
    0.06
    Activations Density 0.001%

    No Known Activations