© 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. 26614
    Prev
    Next
    INDEX
    Explanations

    ensure availability, harm a, famine, sizes and, quality of

    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
    <source
    -0.08
    žÃŃ
    -0.08
    xad
    -0.08
     :,
    -0.08
    ORY
    -0.08
    .isNullOrEmpty
    -0.08
     adversaries
    -0.08
     Gibbs
    -0.08
    linkplain
    -0.08
    ":"","
    -0.07
    POSITIVE LOGITS
    ï½Ĭ
    0.09
    ï½Ĵ
    0.09
    illard
    0.09
     {}".
    0.09
     ¡
    0.09
     {}'.
    0.08
     Shan
    0.08
     prov
    0.08
    )||(
    0.08
     importantly
    0.08
    Activations Density 0.172%

    No Known Activations