© 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. 22752
    Prev
    Next
    INDEX
    Explanations

    no whitespaces or punctuation

    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
     alphanumeric
    -0.12
    ocab
    -0.12
    alphabet
    -0.11
     alphabetical
    -0.11
     parenthesis
    -0.10
     prefixed
    -0.10
    UFFIX
    -0.10
     pronunciation
    -0.09
    atto
    -0.09
     "*.
    -0.09
    POSITIVE LOGITS
     spaces
    0.26
     apost
    0.21
     space
    0.20
    spaces
    0.18
     Spaces
    0.18
     Apost
    0.17
     hy
    0.17
     colon
    0.17
    Spaces
    0.15
     periods
    0.15
    Activations Density 0.415%

    No Known Activations