© 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. 963
    Prev
    Next
    INDEX
    Explanations

    metrics related to health outcomes and environmental factors

    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
    mav
    -0.08
    eid
    -0.07
    ADOS
    -0.07
    699
    -0.07
    Isl
    -0.07
    _epochs
    -0.07
     backgrounds
    -0.07
    enou
    -0.07
    lied
    -0.06
    rych
    -0.06
    POSITIVE LOGITS
    cheng
    0.07
    gettext
    0.06
    .matches
    0.06
     measures
    0.06
    \Queue
    0.06
    amenti
    0.06
    ulton
    0.06
     territorial
    0.06
    ziel
    0.06
     cas
    0.06
    Activations Density 0.021%

    No Known Activations