© 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. 118386
    Prev
    Next
    INDEX
    Explanations

    questions related to legal and judicial matters

    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
    lyn
    -0.07
    eroon
    -0.07
     NSUInteger
    -0.07
    /fixtures
    -0.07
    akens
    -0.07
    ulan
    -0.06
    unami
    -0.06
    gon
    -0.06
    iness
    -0.06
    !(:
    -0.06
    POSITIVE LOGITS
    ätt
    0.07
    andal
    0.06
    ÑĪи
    0.06
    933
    0.06
    ekl
    0.06
    aso
    0.06
    ertainment
    0.06
    ави
    0.06
    htdocs
    0.06
    atz
    0.06
    Activations Density 0.001%

    No Known Activations