© 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. 11597
    Prev
    Next
    INDEX
    Explanations

    can rotate, change, allow

    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
    bish
    -0.10
    ä¸
    -0.09
     taps
    -0.09
    Overflow
    -0.09
    rans
    -0.09
    ANDLE
    -0.09
    ondon
    -0.09
     overloaded
    -0.09
     Inline
    -0.09
    Tap
    -0.09
    POSITIVE LOGITS
     mechanism
    0.18
     mechanisms
    0.15
     deploy
    0.15
     Deploy
    0.15
     deployed
    0.15
     lowering
    0.15
    deploy
    0.15
     retract
    0.14
    Deploy
    0.14
     deploying
    0.14
    Activations Density 0.078%

    No Known Activations