© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 18181
    Prev
    Next
    INDEX
    Explanations

    sentence end punctuation

    np_acts-logits-general · gemini-2.5-flash-lite

    the end of sentences, particularly those concluding with a period followed by closing quotation marks and end-of-turn tokens.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @yooniel31
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.3-70B-IT @ 50-resid-post-gf
    Configuration
    Goodfire/Llama-3.3-70B-Instruct-SAE-l50/Llama-3.3-70B-Instruct-SAE-l50.pt
    Prompts (Dashboard)
    10,000 prompts, 128 tokens each
    Dataset (Dashboard)
    lmsys/lmsys-chat-1m
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erras
    -0.09
    _prim
    -0.09
     sch
    -0.09
     Caucus
    -0.08
    èĶ
    -0.08
    iá»ĥn
    -0.08
    -sort
    -0.08
    935
    -0.08
     UIAlert
    -0.08
    .scalablytyped
    -0.08
    POSITIVE LOGITS
     OR
    0.20
    OR
    0.19
     or
    0.17
     Altern
    0.16
     altern
    0.16
    ï¼ĮæĪĸ
    0.16
     หร
    0.16
     alternatives
    0.15
    æĪĸèĢħ
    0.15
     hoặc
    0.15
    Activations Density 0.085%

    No Known Activations