© 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. 36427
    Prev
    Next
    INDEX
    Explanations

    trained on or using

    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
    apl
    -0.09
    oft
    -0.09
    ONO
    -0.08
    lator
    -0.08
    ude
    -0.08
    æ»
    -0.08
     Ramp
    -0.08
    acks
    -0.08
     Allan
    -0.08
    rs
    -0.08
    POSITIVE LOGITS
     on
    0.12
     trên
    0.12
    ees
    0.11
     på
    0.11
     using
    0.10
     عÙĦÙī
    0.10
    /test
    0.10
    ,test
    0.10
     на
    0.10
     auf
    0.09
    Activations Density 0.034%

    No Known Activations