© 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. 27054
    Prev
    Next
    INDEX
    Explanations

    occurrences of numbers and team participation in events

    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
    ih
    -0.06
     guides
    -0.06
    aur
    -0.06
    öy
    -0.06
     Fallon
    -0.06
     suger
    -0.06
    ehler
    -0.06
     Deutsch
    -0.06
     receivers
    -0.06
     Guides
    -0.06
    POSITIVE LOGITS
     participating
    0.10
     Particip
    0.10
     participants
    0.09
     entries
    0.09
     participant
    0.09
    participants
    0.08
     participation
    0.08
     participate
    0.08
     PARTIC
    0.08
    entries
    0.08
    Activations Density 0.021%

    No Known Activations