© 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. 27170
    Prev
    Next
    INDEX
    Explanations

    references to specific bacterial species and their metabolic properties

    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
    ifen
    -0.07
    ihn
    -0.07
    EMON
    -0.06
    ROTO
    -0.06
    oras
    -0.06
    uentes
    -0.06
    ngo
    -0.06
    erre
    -0.06
    aku
    -0.06
    094
    -0.06
    POSITIVE LOGITS
     spp
    0.09
     species
    0.09
     Species
    0.08
    Species
    0.07
     sp
    0.07
    _sz
    0.07
     okam
    0.06
    Å¡ker
    0.06
    .Constants
    0.06
     nive
    0.06
    Activations Density 0.042%

    No Known Activations