© 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. 121614
    Prev
    Next
    INDEX
    Explanations

    elements related to feeding and baiting in marine environments

    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
    adh
    -0.08
    azor
    -0.07
    quist
    -0.06
    og
    -0.06
     democrat
    -0.05
    quier
    -0.05
     Rodrigo
    -0.05
    .
    -0.05
     cog
    -0.05
    ,
    -0.05
    POSITIVE LOGITS
     bait
    0.11
     lure
    0.11
     attract
    0.10
     attracting
    0.10
     attracts
    0.09
     attraction
    0.09
     enticing
    0.09
     scent
    0.08
     attractiveness
    0.08
     attracted
    0.07
    Activations Density 0.012%

    No Known Activations