© 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. 14123
    Prev
    Next
    INDEX
    Explanations

    the presence of functionally significant punctuation and syntax in code

    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
    oose
    -0.07
    ë²Į
    -0.07
    cela
    -0.07
    ÏģÎŃ
    -0.07
    _unlock
    -0.07
    ensa
    -0.06
    ISR
    -0.06
    okino
    -0.06
    (*)(
    -0.06
    ermo
    -0.06
    POSITIVE LOGITS
    apper
    0.06
    in
    0.06
    ols
    0.06
    elts
    0.05
     gö
    0.05
    iliar
    0.05
    #print
    0.05
    atore
    0.05
    Med
    0.05
    ofil
    0.05
    Activations Density 0.042%

    No Known Activations