© 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. 50684
    Prev
    Next
    INDEX
    Explanations

    shocked speech

    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
     bored
    -0.12
     boredom
    -0.09
    549
    -0.08
    ắt
    -0.08
    chia
    -0.08
    XE
    -0.08
     prop
    -0.08
     nar
    -0.08
     bewild
    -0.08
     unsub
    -0.08
    POSITIVE LOGITS
     shock
    0.30
     shell
    0.30
     Shock
    0.27
     speech
    0.25
     Shell
    0.24
    Shock
    0.22
     Speech
    0.22
    éľĩ
    0.22
    Speech
    0.21
     shocked
    0.21
    Activations Density 0.078%

    No Known Activations