© 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. 20645
    Prev
    Next
    INDEX
    Explanations

    systems, organization, approaches, ways

    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
    ToF
    -0.12
     follando
    -0.09
    orz
    -0.09
    ìľ
    -0.08
    ียà¸ĩ
    -0.08
     обÑıз
    -0.08
     carbohydr
    -0.08
     Reid
    -0.07
    QRST
    -0.07
    ujte
    -0.07
    POSITIVE LOGITS
     ÑĩÑĤобÑĭ
    0.34
     afin
    0.33
     nhằm
    0.32
     inorder
    0.30
     aby
    0.28
     Äijá»ĥ
    0.27
     Ñīоб
    0.25
    为äºĨ
    0.25
     ЧÑĤобÑĭ
    0.20
    ÑĤобÑĭ
    0.20
    Activations Density 0.212%

    No Known Activations