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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 33645
    Prev
    Next
    INDEX
    Explanations

    color alternatives

    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
     violet
    -0.17
    Purple
    -0.17
     Crimson
    -0.17
     crimson
    -0.17
     Purple
    -0.16
     turquoise
    -0.16
    -purple
    -0.16
     Violet
    -0.14
     teal
    -0.12
    purple
    -0.12
    POSITIVE LOGITS
     white
    0.29
     black
    0.24
     brown
    0.22
     gray
    0.22
     grey
    0.22
    çĻ½
    0.20
    white
    0.20
     White
    0.19
     neutral
    0.19
    black
    0.17
    Activations Density 0.070%

    No Known Activations