© 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. 53878
    Prev
    Next
    INDEX
    Explanations

    Russian phrasing, specific characters

    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
    dech
    -0.09
    rollable
    -0.08
     ded
    -0.08
    886
    -0.08
     finer
    -0.08
     equally
    -0.08
    à¸łà¸²à¸Ħ
    -0.08
    wdx
    -0.08
    istrovstvÃŃ
    -0.08
    .tencent
    -0.08
    POSITIVE LOGITS
     cÃłng
    0.53
    è¶Ĭ
    0.48
     ÄįÃŃm
    0.33
     Ñĩем
    0.33
     cuanto
    0.33
     Чем
    0.33
     longer
    0.32
     è¶
    0.28
     Ñĩим
    0.27
     quanto
    0.26
    Activations Density 0.119%

    No Known Activations