© 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. 36223
    Prev
    Next
    INDEX
    Explanations

    requires, typically, may, can, intelligent, name

    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
     isn
    -0.09
     is
    -0.09
    /is
    -0.09
    makes
    -0.09
    oub
    -0.08
    hoe
    -0.08
    zik
    -0.08
     Dow
    -0.08
     awaits
    -0.08
    x
    -0.08
    POSITIVE LOGITS
     able
    0.11
     arou
    0.09
     Will
    0.09
     Cons
    0.09
    IDEO
    0.09
    umbn
    0.09
    NameValuePair
    0.08
    ानत
    0.08
     ragaz
    0.08
    /Runtime
    0.08
    Activations Density 0.197%

    No Known Activations