© 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. 63041
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and structural elements in written text

    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
    ầy
    -0.07
    _METADATA
    -0.07
     sac
    -0.07
    azu
    -0.07
    upe
    -0.06
    ivan
    -0.06
     zbyt
    -0.06
     Shib
    -0.06
    à¹ģล
    -0.06
    ottage
    -0.06
    POSITIVE LOGITS
    utenberg
    0.08
    \Redirect
    0.06
     Wik
    0.06
     Griffith
    0.06
    æŁ±
    0.06
    ror
    0.06
    ienie
    0.06
    HWND
    0.06
    ìĿ´ìĬ¤
    0.06
     Verfüg
    0.06
    Activations Density 0.000%

    No Known Activations