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

    Neuronpedia

    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. 127442
    Prev
    Next
    INDEX
    Explanations

    acronyms and abbreviations related to wildlife research or conservation

    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
     Catalyst
    -0.07
    edio
    -0.06
    ertura
    -0.06
     muse
    -0.06
     Gupta
    -0.06
    )./
    -0.06
    brook
    -0.06
    APA
    -0.06
     pharmacist
    -0.06
    -Col
    -0.06
    POSITIVE LOGITS
    Transmission
    0.07
    EFR
    0.07
     disease
    0.07
     scrap
    0.07
    bookmark
    0.07
    deer
    0.07
     elk
    0.07
    elters
    0.07
    pong
    0.06
     Hunters
    0.06
    Activations Density 0.005%

    No Known Activations