© 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 EvalsExportsAPI 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. 87462
    Prev
    Next
    INDEX
    Explanations

    elements related to animal communication

    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
    826
    -0.07
    apiro
    -0.06
    ekim
    -0.06
    obraz
    -0.06
    mith
    -0.06
     Institution
    -0.06
     diversion
    -0.06
     institution
    -0.06
    lum
    -0.06
    289
    -0.06
    POSITIVE LOGITS
    onal
    0.07
    ulous
    0.07
     heard
    0.07
     nasal
    0.06
     territorial
    0.06
     cad
    0.06
    anda
    0.06
     ocas
    0.06
     ********************************************************************************
    0.06
    _DECLARE
    0.06
    Activations Density 0.006%

    No Known Activations