© 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. 31621
    Prev
    Next
    INDEX
    Explanations

    punctuation and exclamation 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
     therefore
    -0.11
     hence
    -0.09
     Therefore
    -0.09
     thus
    -0.08
    Therefore
    -0.08
     must
    -0.07
     yet
    -0.07
     donc
    -0.07
     Hence
    -0.06
    ,
    -0.06
    POSITIVE LOGITS
    åIJ¦
    0.10
     OTHERWISE
    0.09
    Alternatively
    0.09
    llib
    0.09
     otherwise
    0.08
    promise
    0.08
    askan
    0.08
    StandardItem
    0.08
     Alternatively
    0.08
     Otherwise
    0.08
    Activations Density 0.030%

    No Known Activations