© 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. 90101
    Prev
    Next
    INDEX
    Explanations

    proper names, particularly those of people

    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
    ylvania
    -0.08
    eler
    -0.08
    eval
    -0.07
    etype
    -0.07
    ectomy
    -0.07
    es
    -0.07
    ela
    -0.07
    urf
    -0.07
    ingroup
    -0.07
    DOMNode
    -0.07
    POSITIVE LOGITS
    dehyde
    0.09
    ais
    0.08
    tings
    0.07
    culated
    0.07
    umni
    0.07
    da
    0.07
    igned
    0.07
    adium
    0.07
    dea
    0.07
    gary
    0.07
    Activations Density 0.054%

    No Known Activations