Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 125631
    Prev
    Next
    INDEX
    Explanations

    references to global or comprehensive concepts, particularly in relation to ethics and credibility

    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
    348
    -0.07
    273
    -0.07
    573
    -0.07
    /browse
    -0.06
    735
    -0.06
    139
    -0.06
     fas
    -0.06
    ÙĦØŃ
    -0.06
    871
    -0.06
     Trials
    -0.06
    POSITIVE LOGITS
    ragen
    0.07
    omik
    0.07
    ocument
    0.07
    ront
    0.07
    ukan
    0.07
    DonaldTrump
    0.07
    romo
    0.07
    uese
    0.06
    gency
    0.06
    usta
    0.06
    Activations Density 0.000%

    No Known Activations