© 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. 27035
    Prev
    Next
    INDEX
    Explanations

    extract file name from a path

    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
     renamed
    -0.10
     synonyms
    -0.10
    anyak
    -0.10
    å§ĵ
    -0.10
    alphabet
    -0.10
    /stretch
    -0.10
     Alphabet
    -0.10
     alphabet
    -0.10
    åŃĹ
    -0.09
     vowels
    -0.09
    POSITIVE LOGITS
     format
    0.22
     string
    0.18
     formats
    0.18
    æł¼å¼ı
    0.16
     Format
    0.15
     strings
    0.15
    string
    0.14
     representation
    0.14
    åŃĹ符串
    0.14
    -string
    0.14
    Activations Density 0.237%

    No Known Activations