© 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. 26677
    Prev
    Next
    INDEX
    Explanations

    would have

    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
    oder
    -0.10
    stry
    -0.10
    ãĢĢãĤĿ
    -0.09
    rek
    -0.09
    åĪĨåĪ«
    -0.08
    å¼ĢæĶ¾
    -0.08
     Moran
    -0.08
     struggle
    -0.08
    Alchemy
    -0.08
     Bryan
    -0.08
    POSITIVE LOGITS
    è¿Ľè¡Į
    0.17
    éĢ²è¡Į
    0.16
     numa
    0.14
    æĺ¯ä¸Ģ个
    0.14
     engaged
    0.13
     melakukan
    0.12
    ãģ«ãĤĪãĤĭ
    0.12
    æľīä¸Ģ
    0.11
     conducting
    0.11
     realizar
    0.11
    Activations Density 0.304%

    No Known Activations