© 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. 54689
    Prev
    Next
    INDEX
    Explanations

    become, harden, soften, dry

    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
    bt
    -0.10
     exc
    -0.10
     Fal
    -0.10
    ãģ«ãģĹãģ¦
    -0.09
    åĨ²
    -0.09
    ilt
    -0.09
     van
    -0.09
    Fal
    -0.09
     loosen
    -0.09
    åĪ»
    -0.09
    POSITIVE LOGITS
     become
    0.18
     becomes
    0.16
     becoming
    0.14
     menjadi
    0.13
     Become
    0.13
    bec
    0.13
    åıĺå¾Ĺ
    0.12
     trợ
    0.12
     became
    0.12
     shr
    0.12
    Activations Density 0.080%

    No Known Activations