© 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. 1392
    Prev
    Next
    INDEX
    Explanations

    be critical, downregulated

    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
     elect
    -0.11
     lid
    -0.11
     Lid
    -0.11
     recom
    -0.11
     genomic
    -0.10
     mut
    -0.10
     unb
    -0.10
     rig
    -0.09
     Kitt
    -0.09
     mismatch
    -0.09
    POSITIVE LOGITS
     expression
    0.29
    expression
    0.25
     Expression
    0.23
    Expression
    0.21
    -expression
    0.19
    (expression
    0.19
     genes
    0.18
     expressions
    0.18
    _expression
    0.17
     expres
    0.17
    Activations Density 0.054%

    No Known Activations