© 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. 1015
    Prev
    Next
    INDEX
    Explanations

    includes, lists, documentation

    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
    ulet
    -0.09
    ä»»ä½ķ
    -0.09
     supra
    -0.08
    ses
    -0.08
    egt
    -0.08
    .recycle
    -0.08
     or
    -0.08
    onga
    -0.08
     Hlav
    -0.08
    obec
    -0.08
    POSITIVE LOGITS
    requested
    0.13
     requested
    0.12
    Requested
    0.11
    _requested
    0.10
     added
    0.10
     suggested
    0.10
     myself
    0.10
     liberties
    0.09
     emphasis
    0.09
    outu
    0.09
    Activations Density 0.155%

    No Known Activations