© 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. 26186
    Prev
    Next
    INDEX
    Explanations

    cyrillic letter sequences

    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
    ãĢ
    -0.11
    mos
    -0.11
    ering
    -0.10
    iento
    -0.10
    h
    -0.10
    458
    -0.10
    mar
    -0.09
    ema
    -0.09
    anking
    -0.09
    ables
    -0.09
    POSITIVE LOGITS
    надлеж
    0.15
    âĦĸâĦĸ
    0.12
    .scalablytyped
    0.12
    èIJ½
    0.11
    elease
    0.10
     nuest
    0.10
    usk
    0.10
    .Undef
    0.10
    aÄį
    0.09
    \tROM
    0.09
    Activations Density 0.043%

    No Known Activations