© 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. 5765
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly periods and question marks

    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
    ovah
    -0.07
    odzi
    -0.07
    manship
    -0.07
    asel
    -0.06
    825
    -0.06
    addock
    -0.06
    pin
    -0.06
    anova
    -0.06
    715
    -0.06
    žit
    -0.06
    POSITIVE LOGITS
    erif
    0.07
    alles
    0.06
     Oval
    0.06
    Ĺ
    0.06
     Workflow
    0.06
     TCHAR
    0.06
     Hubb
    0.06
    alsy
    0.06
     Cousins
    0.06
     complement
    0.06
    Activations Density 0.001%

    No Known Activations