© 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. 26895
    Prev
    Next
    INDEX
    Explanations

    ending tokens or delimiters in a structured document

    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
    iec
    -0.08
    iid
    -0.07
    swer
    -0.06
    pect
    -0.06
    ими
    -0.06
    eriod
    -0.06
     Transcript
    -0.06
    FRING
    -0.06
    ymbol
    -0.06
     Pron
    -0.06
    POSITIVE LOGITS
    odore
    0.08
    ÙħاÙĦ
    0.07
    gate
    0.06
    åı¬
    0.06
    oreach
    0.06
    kker
    0.06
    afc
    0.06
    ustum
    0.06
    case
    0.06
    s
    0.06
    Activations Density 0.003%

    No Known Activations