© 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. 59985
    Prev
    Next
    INDEX
    Explanations

    global to local scale

    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
    YRO
    -0.09
     :/:
    -0.09
    /stdc
    -0.09
    __("
    -0.09
    FIELDS
    -0.09
    ibox
    -0.09
    577
    -0.08
    èĮĤ
    -0.08
    ãĤŀ
    -0.08
    unga
    -0.08
    POSITIVE LOGITS
     level
    0.29
     scale
    0.20
    level
    0.16
     basis
    0.16
     Scale
    0.16
     ÑĥÑĢовне
    0.15
     stage
    0.15
     niveau
    0.13
     fashion
    0.13
     Level
    0.13
    Activations Density 0.090%

    No Known Activations