© 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. 56703
    Prev
    Next
    INDEX
    Explanations

    calculate statistics or formulas

    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
    enor
    -0.10
    ascar
    -0.09
     undermin
    -0.09
    Neal
    -0.09
    _prep
    -0.09
     statistics
    -0.08
     automobiles
    -0.08
     Lever
    -0.08
     Neal
    -0.08
    AVING
    -0.08
    POSITIVE LOGITS
     formula
    0.26
    åħ¬å¼ı
    0.21
     Formula
    0.19
    formula
    0.19
    Formula
    0.18
     formulas
    0.18
     factors
    0.18
     calc
    0.16
     калÑĮ
    0.16
    _formula
    0.16
    Activations Density 0.188%

    No Known Activations