© 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. 31849
    Prev
    Next
    INDEX
    Explanations

    alternatives or choices

    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
    /or
    -0.19
     also
    -0.10
    lap
    -0.10
    elez
    -0.10
    ä¹Łæľī
    -0.09
     both
    -0.09
    olv
    -0.09
     także
    -0.09
     ê·¸ëĥ¥
    -0.09
    cela
    -0.08
    POSITIVE LOGITS
     any
    0.24
    ifice
    0.22
    ients
    0.22
     anything
    0.22
    phans
    0.21
     indeed
    0.21
    ä»»ä½ķ
    0.19
     nor
    0.19
     ANY
    0.18
     else
    0.18
    Activations Density 0.113%

    No Known Activations