© 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. 64239
    Prev
    Next
    INDEX
    Explanations

    causing or becoming

    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
    chin
    -0.10
    å¯¾å¿ľ
    -0.10
     enc
    -0.10
    uni
    -0.10
     targets
    -0.10
     Preservation
    -0.09
     Palmer
    -0.09
     обÑĢаÑī
    -0.09
    UTTON
    -0.09
    oto
    -0.09
    POSITIVE LOGITS
     vice
    0.17
     causing
    0.14
     cause
    0.14
     Vice
    0.11
     either
    0.11
    cause
    0.11
    导èĩ´
    0.10
    vice
    0.10
    hasil
    0.09
    rawn
    0.09
    Activations Density 0.079%

    No Known Activations