© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 13591
    Prev
    Next
    INDEX
    Explanations

    heard coming

    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
     &);\n
    -0.09
    çŃĴ
    -0.09
    dst
    -0.08
    impl
    -0.08
    259
    -0.08
    DAO
    -0.08
    remium
    -0.08
    _gradients
    -0.08
     grounds
    -0.08
    veau
    -0.08
    POSITIVE LOGITS
     footsteps
    0.27
     heard
    0.23
     door
    0.20
    heard
    0.19
     hear
    0.17
    éŨ
    0.17
     hears
    0.16
     Foot
    0.16
     Heard
    0.16
    Foot
    0.15
    Activations Density 0.040%

    No Known Activations