© 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. 3415
    Prev
    Next
    INDEX
    Explanations

    terms related to legal topics and criminal justice

    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
     moder
    -0.06
    سÙĨ
    -0.06
    ova
    -0.06
    вÑĸ
    -0.06
    alu
    -0.06
    adio
    -0.06
    ago
    -0.05
    azen
    -0.05
    2
    -0.05
    er
    -0.05
    POSITIVE LOGITS
     discret
    0.08
     overview
    0.07
    Fcn
    0.07
    ġ
    0.07
    ureau
    0.07
    overview
    0.07
    OpenHelper
    0.07
    -summary
    0.07
    semblies
    0.06
    ileo
    0.06
    Activations Density 0.007%

    No Known Activations