© 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. 9317
    Prev
    Next
    INDEX
    Explanations

    reasoning and explanation

    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
    ormsg
    -0.09
    ICY
    -0.09
    ıf
    -0.09
    acades
    -0.08
    alloca
    -0.08
    itched
    -0.08
    .Lib
    -0.08
    pcf
    -0.08
    ï½Ģãĥ½
    -0.08
    <|begin_of_text|>
    -0.08
    POSITIVE LOGITS
     why
    0.19
    why
    0.16
     behind
    0.15
     nor
    0.14
     reasons
    0.14
    为ä»Ģä¹Ī
    0.13
     supporting
    0.13
     pourquoi
    0.12
     Why
    0.12
    çIJĨçĶ±
    0.12
    Activations Density 0.019%

    No Known Activations