© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 59880
    Prev
    Next
    INDEX
    Explanations

    terms related to animal behavior and ecology

    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
     overseas
    -0.07
    ertas
    -0.06
    :
    -0.06
     pur
    -0.06
    pur
    -0.06
    725
    -0.06
    port
    -0.06
     experiment
    -0.06
    heat
    -0.06
     Overse
    -0.06
    POSITIVE LOGITS
    ì·¨
    0.07
    -INF
    0.07
    ..↵↵↵↵
    0.07
    Ïİν
    0.07
    isoft
    0.07
     (~(
    0.07
    OKIE
    0.07
    catch
    0.07
    createCommand
    0.07
    ofday
    0.07
    Activations Density 0.012%

    No Known Activations