© 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. 31458
    Prev
    Next
    INDEX
    Explanations

    instances of punctuation and its interaction with text structure

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     âĢ»
    -0.07
    ¬Ĥ
    -0.06
     ranges
    -0.06
    åľŃ
    -0.06
    ioni
    -0.06
    åĻ¨
    -0.06
     {}:
    -0.06
    including
    -0.06
    leep
    -0.06
     ranging
    -0.06
    POSITIVE LOGITS
    rowable
    0.08
     because
    0.07
    because
    0.07
    aris
    0.06
    matching
    0.06
     ÙħاÛĮÙĦ
    0.06
    åįģåħŃ
    0.06
    offsetof
    0.06
     Hew
    0.06
     ÙĨسبة
    0.06
    Activations Density 0.028%

    No Known Activations