© 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. 53676
    Prev
    Next
    INDEX
    Explanations

    entropy $H(Z)$

    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
     deterministic
    -0.10
    emean
    -0.09
     Kong
    -0.09
     sag
    -0.09
    osoph
    -0.09
     harc
    -0.09
     congr
    -0.09
    å®
    -0.08
     probabil
    -0.08
     BoxFit
    -0.08
    POSITIVE LOGITS
     Shannon
    0.38
     entropy
    0.30
     Ent
    0.29
    Entropy
    0.26
     ent
    0.25
    ç
    0.25
    entropy
    0.24
     ENT
    0.20
    _entropy
    0.20
    Ent
    0.19
    Activations Density 0.038%

    No Known Activations