© 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. 2852
    Prev
    Next
    INDEX
    Explanations

    sound out letters or words

    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
     interp
    -0.11
    AYOUT
    -0.10
     grammar
    -0.10
     Grammar
    -0.10
    å¯Ħ
    -0.09
     Tet
    -0.09
    grammar
    -0.09
    unden
    -0.09
     Lover
    -0.09
    ainting
    -0.09
    POSITIVE LOGITS
     Sounds
    0.17
     sounds
    0.17
     sound
    0.15
    Sounds
    0.14
     Sound
    0.13
    ophon
    0.13
     blends
    0.13
     sounded
    0.13
    sounds
    0.12
    Sound
    0.12
    Activations Density 0.059%

    No Known Activations