© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 32571
    Prev
    Next
    INDEX
    Explanations

    a followed by positive descriptions

    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
    926
    -0.09
     hallmark
    -0.09
     Morg
    -0.09
     Äijâu
    -0.09
    uzzle
    -0.09
     cornerstone
    -0.09
     quint
    -0.08
     larg
    -0.08
     ÙħØ«
    -0.08
     coquine
    -0.08
    POSITIVE LOGITS
     success
    0.22
     breeze
    0.18
     pleasure
    0.18
     treat
    0.17
     blast
    0.15
     sight
    0.15
    success
    0.15
    irt
    0.15
    -ok
    0.14
     Success
    0.13
    Activations Density 0.053%

    No Known Activations