© 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. 58826
    Prev
    Next
    INDEX
    Explanations

    of the

    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
    /Dk
    -0.10
    âĶ¬
    -0.08
    iÃŃ
    -0.08
    Ģ
    -0.08
    RAINT
    -0.07
    CallCheck
    -0.07
     ÃĶ
    -0.07
     sourceMapping
    -0.07
    antino
    -0.07
    ¶Į
    -0.07
    POSITIVE LOGITS
     ``
    0.09
    ô
    0.09
    [âĢ¦
    0.09
    ê¸Ķ
    0.08
     Dove
    0.08
    é§IJ
    0.08
    .Dom
    0.07
    endum
    0.07
     ï¼ļ
    0.07
    ãĢģãĢģ
    0.07
    Activations Density 0.430%

    No Known Activations