© 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. 36005
    Prev
    Next
    INDEX
    Explanations

    variety of options

    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
     =>$
    -0.07
    abi
    -0.07
    Äįet
    -0.07
    alet
    -0.07
    [href
    -0.07
    keh
    -0.07
    ÌĨ
    -0.07
    rede
    -0.06
    etter
    -0.06
    erva
    -0.06
    POSITIVE LOGITS
    ActionCreators
    0.09
    ï¼ģï¼ģ\n\n
    0.08
    Extern
    0.07
    ĴĮ
    0.07
    _flg
    0.07
    .mybatisplus
    0.07
    AdapterFactory
    0.07
    anken
    0.07
    aload
    0.07
    HasBeen
    0.07
    Activations Density 0.067%

    No Known Activations