© 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. 38196
    Prev
    Next
    INDEX
    Explanations

    patterns of punctuation marks and periods

    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
     otherwise
    -0.06
     nail
    -0.06
    iff
    -0.06
     --
    -0.06
    -
    -0.06
    ↵
    -0.05
    İ·
    -0.05
     interes
    -0.05
     accessory
    -0.05
     -
    -0.05
    POSITIVE LOGITS
    á»ĵn
    0.08
     оно
    0.08
    oleÄį
    0.08
     jspb
    0.08
    ساب
    0.08
    mojom
    0.08
    LEMENT
    0.08
    ắm
    0.07
    CORD
    0.07
    illet
    0.07
    Activations Density 0.013%

    No Known Activations