© 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. 59323
    Prev
    Next
    INDEX
    Explanations

    numerical data and categories related to animal behavior and characteristics

    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
     *)((
    -0.08
    vais
    -0.07
    wner
    -0.07
    etri
    -0.07
    orris
    -0.07
    [__
    -0.07
    Fuse
    -0.07
     PROGMEM
    -0.07
     Ferguson
    -0.07
    erable
    -0.07
    POSITIVE LOGITS
     Kingdom
    0.06
     precip
    0.06
    uell
    0.06
    king
    0.06
    udo
    0.05
    )did
    0.05
     radio
    0.05
     kingdom
    0.05
     ranges
    0.05
    hood
    0.05
    Activations Density 0.004%

    No Known Activations