© 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. 69188
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, specifically periods and their frequency

    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
     سÙĦاÙħت
    -0.07
    uju
    -0.07
    	TokenName
    -0.07
    askell
    -0.07
    adors
    -0.07
    ippo
    -0.07
    .Disclaimer
    -0.07
    æĪ¸
    -0.07
    zie
    -0.06
    Æ¡m
    -0.06
    POSITIVE LOGITS
    onium
    0.06
    ÙĪار
    0.06
    umb
    0.06
     Kop
    0.06
     (;;)
    0.05
    bsp
    0.05
    olib
    0.05
    til
    0.05
     habitat
    0.05
    UMB
    0.05
    Activations Density 0.000%

    No Known Activations