© 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. 27561
    Prev
    Next
    INDEX
    Explanations

    a rough, possible, suggested

    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
     exactly
    -0.11
    erus
    -0.10
    fy
    -0.09
    rous
    -0.09
     exact
    -0.09
    ye
    -0.09
     prospects
    -0.09
     Maul
    -0.09
    wang
    -0.09
    obe
    -0.09
    POSITIVE LOGITS
     attempt
    0.23
     rough
    0.22
    ç²Ĺ
    0.17
     attempted
    0.17
     approximation
    0.17
    attempt
    0.17
     possible
    0.16
    ROUGH
    0.16
     approx
    0.15
     Attempt
    0.15
    Activations Density 0.224%

    No Known Activations