© 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. 93591
    Prev
    Next
    INDEX
    Explanations

    themes related to legal proceedings and due process

    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
    onica
    -0.09
    incare
    -0.07
    ansion
    -0.07
    ÑĢÑĮ
    -0.07
    ivec
    -0.07
    coni
    -0.07
    vester
    -0.07
    pler
    -0.07
    IODevice
    -0.07
    usters
    -0.06
    POSITIVE LOGITS
     conflicts
    0.10
     Conflict
    0.09
     conflict
    0.09
     disclosure
    0.09
     impartial
    0.08
     transparency
    0.08
     Disclosure
    0.08
     nep
    0.08
     disclosures
    0.07
     Ethics
    0.07
    Activations Density 0.046%

    No Known Activations