© 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
    2. Llama3.3-70B-IT
    3. 50-RESID-POST-GF
    4. 9488
    Prev
    Next
    INDEX
    Explanations

    ìĪĺ followed by ì¹ĺëĬĶ or ìĦ±

    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
    geber
    -0.10
     ë¸
    -0.10
    .NewLine
    -0.10
    arel
    -0.10
    |--
    -0.09
    urat
    -0.09
     Laugh
    -0.09
    jes
    -0.09
    ots
    -0.09
     Isles
    -0.09
    POSITIVE LOGITS
    enance
    0.11
    (æ°´
    0.11
    IFS
    0.10
    illance
    0.10
    _infos
    0.09
     pháºŃn
    0.09
    velt
    0.08
    erre
    0.08
    å̤
    0.08
    /Dk
    0.08
    Activations Density 0.019%

    No Known Activations