© 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. 57036
    Prev
    Next
    INDEX
    Explanations

    references to legal actions and lawsuits

    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
    uellen
    -0.07
    xCD
    -0.07
    lections
    -0.07
    STALL
    -0.07
    escal
    -0.07
    ulace
    -0.07
    ichick
    -0.07
     Qed
    -0.07
    studio
    -0.07
    unate
    -0.07
    POSITIVE LOGITS
     class
    0.09
     consumer
    0.08
     group
    0.07
     collective
    0.07
     lead
    0.07
     Class
    0.06
     discovery
    0.06
     groups
    0.06
     classes
    0.06
    .class
    0.06
    Activations Density 0.015%

    No Known Activations