© 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. 35679
    Prev
    Next
    INDEX
    Explanations

    generally not, may not, is not

    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
     Impossible
    -0.16
     impossible
    -0.15
    Impossible
    -0.15
     inability
    -0.14
     imposs
    -0.13
     Cannot
    -0.13
     невозможно
    -0.13
     unable
    -0.13
    $MESS
    -0.12
     Unable
    -0.12
    POSITIVE LOGITS
    ä¸įæĺ¯
    0.21
    ä¸į好
    0.20
     uns
    0.20
     isn
    0.20
    并ä¸į
    0.19
     wasn
    0.19
    æĺ¯ä¸į
    0.17
     bad
    0.17
     aren
    0.16
     nicht
    0.16
    Activations Density 0.167%

    No Known Activations