© 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. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 18715
    Prev
    Next
    INDEX
    Explanations

    space between

    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
    Negative Logits
     brackets
    -0.12
    orners
    -0.10
     paren
    -0.10
     parentheses
    -0.09
     Inline
    -0.09
     parenthesis
    -0.09
     Bracket
    -0.08
     bracket
    -0.08
     segregated
    -0.08
    ommen
    -0.08
    POSITIVE LOGITS
     between
    0.25
     spaces
    0.22
     space
    0.22
     междÑĥ
    0.21
     Between
    0.19
     giữa
    0.19
     Space
    0.18
    space
    0.18
    Between
    0.18
    between
    0.18
    Activations Density 0.065%

    No Known Activations