© 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. 59067
    Prev
    Next
    INDEX
    Explanations

    deep understanding or precise perception

    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
    kj
    -0.10
     familiar
    -0.09
     gá»įn
    -0.08
    alia
    -0.08
     VÅ¡
    -0.08
    -
    -0.08
     Dock
    -0.08
    iona
    -0.08
    ï½Ĵ
    -0.08
    æIJŃ
    -0.08
    POSITIVE LOGITS
     deeper
    0.24
     deep
    0.21
     better
    0.19
     thorough
    0.17
     глÑĥб
    0.16
     understanding
    0.16
    æ·±
    0.16
     sâu
    0.15
     deepest
    0.15
     handle
    0.14
    Activations Density 0.025%

    No Known Activations