© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 91528
    Prev
    Next
    INDEX
    Explanations

    terms related to animal behavior and survival adaptations

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    plen
    -0.07
     Seal
    -0.07
     demi
    -0.07
    563
    -0.06
    alfa
    -0.06
    fad
    -0.06
    vette
    -0.06
    ezier
    -0.06
    vrier
    -0.06
    egin
    -0.06
    POSITIVE LOGITS
     defensive
    0.08
     Defensive
    0.08
     defended
    0.07
     defensively
    0.07
     defense
    0.07
     Loren
    0.07
     mimic
    0.07
    PHPUnit
    0.06
    -defense
    0.06
    aso
    0.06
    Activations Density 0.003%

    No Known Activations