© 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. 108766
    Prev
    Next
    INDEX
    Explanations

    terminal punctuation, specifically periods

    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
     Lou
    -0.07
     Norris
    -0.06
    id
    -0.06
    iek
    -0.06
    ing
    -0.06
     Fro
    -0.06
     Rash
    -0.06
    in
    -0.06
     undef
    -0.05
     grit
    -0.05
    POSITIVE LOGITS
    éĢ¸
    0.08
    ensus
    0.07
    -UA
    0.07
    оÑģк
    0.07
    mlink
    0.07
    ¤
    0.07
    gas
    0.07
    portun
    0.07
     bÃł
    0.07
    elli
    0.07
    Activations Density 0.000%

    No Known Activations