© 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. 58879
    Prev
    Next
    INDEX
    Explanations

    geological, hell, ecstasy, drunk, cheat

    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
     salopes
    -0.12
     Barack
    -0.11
    anford
    -0.10
     Bookmark
    -0.10
    .scalablytyped
    -0.10
    _PUSHDATA
    -0.09
    strup
    -0.09
     foul
    -0.09
    ç¢
    -0.09
    elsinki
    -0.09
    POSITIVE LOGITS
     certain
    0.15
     infamous
    0.11
     Certain
    0.11
     certains
    0.10
     Mein
    0.10
    480
    0.10
    Certain
    0.10
     Chern
    0.10
     nuclear
    0.10
     worse
    0.10
    Activations Density 0.189%

    No Known Activations