© 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. 9649
    Prev
    Next
    INDEX
    Explanations

    initial value, breadth-first, denial of service, rapid eye, finite element

    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
     Whip
    -0.09
     Malik
    -0.09
    ">//
    -0.09
    IRROR
    -0.08
    .ElementAt
    -0.08
    obel
    -0.08
     awakeFromNib
    -0.08
     Hend
    -0.08
    assy
    -0.08
     Passport
    -0.08
    POSITIVE LOGITS
    ¶Į
    0.13
    ãĤŀ
    0.09
    ombs
    0.09
    omanip
    0.09
     Fra
    0.08
     اÙĦÙħتØŃدة
    0.08
     Mug
    0.08
     Eh
    0.08
    :\/\/
    0.08
     twig
    0.08
    Activations Density 0.143%

    No Known Activations