© 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. 42188
    Prev
    Next
    INDEX
    Explanations

    internal dialogues with imaginary characters

    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
     underst
    -0.10
    _resume
    -0.09
    aunch
    -0.09
     جا
    -0.08
    æĬľ
    -0.08
     NEC
    -0.08
     conqu
    -0.08
     nek
    -0.08
    vard
    -0.08
     Bacon
    -0.08
    POSITIVE LOGITS
     voices
    0.26
     inner
    0.25
     voice
    0.25
     Inner
    0.22
     Voice
    0.21
    voice
    0.19
    Voice
    0.19
     internal
    0.19
    inner
    0.18
     INNER
    0.18
    Activations Density 0.099%

    No Known Activations