© 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. 304
    Prev
    Next
    INDEX
    Explanations

    Probability of Capturing

    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
    /py
    -0.13
    /pub
    -0.12
    /pi
    -0.12
    pig
    -0.12
    /play
    -0.12
    /Page
    -0.12
    /pass
    -0.12
    /pay
    -0.11
    pkg
    -0.11
    /part
    -0.11
    POSITIVE LOGITS
    _P
    0.29
    ÂłP
    0.28
     P
    0.27
    .P
    0.24
    \tP
    0.23
    -p
    0.23
    P
    0.23
     ÐŁ
    0.22
    -P
    0.22
     p
    0.22
    Activations Density 0.331%

    No Known Activations