© 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. 4079
    Prev
    Next
    INDEX
    Explanations

    it could be that

    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
     Reynolds
    -0.09
     weakest
    -0.09
     lifestyle
    -0.09
     Lifestyle
    -0.09
     corrupt
    -0.09
     communities
    -0.09
     connections
    -0.09
     комплек
    -0.08
     सà¤ļ
    -0.08
    yii
    -0.08
    POSITIVE LOGITS
     employee
    0.12
     incidents
    0.12
     colleg
    0.12
     department
    0.12
     mic
    0.12
     raises
    0.11
     Raises
    0.11
     climate
    0.10
    FFECT
    0.10
     atmosphere
    0.10
    Activations Density 0.141%

    No Known Activations