© 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. 31553
    Prev
    Next
    INDEX
    Explanations

    state of being or completion

    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
    .isActive
    -0.09
    Unchecked
    -0.09
    enie
    -0.09
    .qual
    -0.08
    iguous
    -0.08
    acre
    -0.08
    inant
    -0.08
    αιν
    -0.08
     exponent
    -0.08
    dge
    -0.08
    POSITIVE LOGITS
    Fully
    0.21
     Fully
    0.21
     fully
    0.20
    fully
    0.18
     heavily
    0.15
    é«ĺ度
    0.12
     Highly
    0.11
     properly
    0.11
     estar
    0.11
     highly
    0.11
    Activations Density 0.199%

    No Known Activations