© 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. 56164
    Prev
    Next
    INDEX
    Explanations

    not necessarily mean

    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
     Zig
    -0.09
     diabetic
    -0.09
     doubly
    -0.09
    rets
    -0.09
     Gibson
    -0.09
    adem
    -0.09
     advent
    -0.09
    iali
    -0.08
    emm
    -0.08
     eventually
    -0.08
    POSITIVE LOGITS
     necessarily
    0.30
     mean
    0.27
     means
    0.21
    mean
    0.20
     automatically
    0.20
    ecessarily
    0.18
     Mean
    0.18
    æĦıåij³
    0.17
    .mean
    0.16
     meant
    0.16
    Activations Density 0.030%

    No Known Activations