© 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. 39388
    Prev
    Next
    INDEX
    Explanations

    feasibility, potential, impact

    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
     specificity
    -0.12
     versatility
    -0.11
     responsiveness
    -0.10
     usable
    -0.10
     uniqueness
    -0.09
     Laure
    -0.09
    âĸį
    -0.09
    loid
    -0.09
     Responsibilities
    -0.09
    âĸı
    -0.09
    POSITIVE LOGITS
    feas
    0.29
     wisdom
    0.27
     Fe
    0.26
     advis
    0.25
     feasibility
    0.22
     feas
    0.22
     pract
    0.22
    Fe
    0.21
     des
    0.20
     propri
    0.20
    Activations Density 0.161%

    No Known Activations