© 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. 37389
    Prev
    Next
    INDEX
    Explanations

    On the other hand, X refers to

    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
    edback
    -0.09
    unsch
    -0.09
    odo
    -0.09
    yah
    -0.08
     dabei
    -0.08
    lest
    -0.08
    MUX
    -0.08
    ï¼Ŀ
    -0.08
    dux
    -0.08
    regunta
    -0.08
    POSITIVE LOGITS
     naopak
    0.16
    åīĩ
    0.15
    åĪĻ
    0.15
     instead
    0.14
    ãģĵãģ¡ãĤī
    0.14
     meanwhile
    0.13
    æĽ´åĬł
    0.12
     convers
    0.11
    åı¦ä¸Ģ
    0.11
     ALSO
    0.11
    Activations Density 0.069%

    No Known Activations