© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 23564
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by words

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    Opens
    -0.09
    elas
    -0.09
     segregated
    -0.09
    onto
    -0.08
    ical
    -0.08
     anh
    -0.08
    emy
    -0.08
     Impl
    -0.08
     Nir
    -0.08
    strup
    -0.08
    POSITIVE LOGITS
    âĢIJâĢIJ
    0.10
    avou
    0.09
    ÅĻád
    0.09
    rbrace
    0.09
    <()>
    0.09
    åįĪ
    0.09
    614
    0.08
    please
    0.08
    æ§
    0.08
    =end
    0.08
    Activations Density 0.000%

    No Known Activations