© 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. 71519
    Prev
    Next
    INDEX
    Explanations

    occurrences of financial and transactional activities

    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
    atted
    -0.07
    marked
    -0.07
    ingly
    -0.06
    etr
    -0.06
     was
    -0.06
    ally
    -0.06
    .sap
    -0.06
     wasn
    -0.06
     quant
    -0.06
     sne
    -0.06
    POSITIVE LOGITS
    rops
    0.08
    wap
    0.08
    unker
    0.07
    ós
    0.07
    dy
    0.07
    prites
    0.07
    oge
    0.07
    IER
    0.07
    æµ´
    0.07
    ENS
    0.06
    Activations Density 0.023%

    No Known Activations