© 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. 15-LLAMASCOPE-RES-131K
    11. 62100
    Prev
    Next
    INDEX
    Explanations

    references to court rulings and legal proceedings

    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
    ucha
    -0.07
    Ĵ
    -0.07
    é¬
    -0.07
     appellate
    -0.07
    Mounted
    -0.07
    idla
    -0.06
    éģĭåĭķ
    -0.06
    .addTarget
    -0.06
     alta
    -0.06
    istas
    -0.06
    POSITIVE LOGITS
     lower
    0.07
    zung
    0.07
    arness
    0.06
    ductive
    0.06
    duct
    0.06
     originally
    0.06
    /original
    0.06
    æĬķ注
    0.06
     original
    0.06
    npj
    0.06
    Activations Density 0.024%

    No Known Activations