© 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. 77541
    Prev
    Next
    INDEX
    Explanations

    terms related to ecology and environmental studies

    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
    addock
    -0.07
    onor
    -0.07
    гл
    -0.07
    ertia
    -0.07
    ë¹
    -0.07
    liner
    -0.07
    ebo
    -0.07
    ingleton
    -0.07
    .tech
    -0.07
    Wunused
    -0.07
    POSITIVE LOGITS
    /ec
    0.10
    /environment
    0.08
     friendly
    0.08
    -minded
    0.07
    bett
    0.07
    (EC
    0.07
    -friendly
    0.07
     minded
    0.07
    umen
    0.07
     Friendly
    0.06
    Activations Density 0.005%

    No Known Activations