© 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. 9772
    Prev
    Next
    INDEX
    Explanations

    list of information, causes, reasons, steps

    np_acts-logits-general · gemini-2.5-flash-lite

    informative or explanatory statements that introduce lists, explanations, or helpful responses.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @yooniel31
    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
     %[
    -0.12
     ragaz
    -0.09
     [âĢ¦
    -0.08
    ebek
    -0.08
    ï¿
    -0.07
    Lorem
    -0.07
    imator
    -0.07
     "><
    -0.07
    ï½ŀï½ŀ
    -0.07
    ãĥ¼ãĥ¼
    -0.07
    POSITIVE LOGITS
    ÂŃi
    0.10
    &apos
    0.08
     EXEMPLARY
    0.08
    taj
    0.08
    URLException
    0.08
                                                \n
    0.08
     smr
    0.08
    âĢħ
    0.08
    endereco
    0.08
                           \n
    0.07
    Activations Density 13.695%

    No Known Activations