© 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. 54500
    Prev
    Next
    INDEX
    Explanations

    ensure validity and accuracy

    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
     reg
    -0.10
     lag
    -0.09
     expl
    -0.09
     mystery
    -0.09
     doc
    -0.09
     facts
    -0.09
    zn
    -0.09
     examples
    -0.08
    iel
    -0.08
     alm
    -0.08
    POSITIVE LOGITS
     valid
    0.22
     conclusions
    0.19
    valid
    0.18
    -valid
    0.18
     accurate
    0.17
     validity
    0.17
     reliability
    0.17
     Valid
    0.17
     accuracy
    0.16
    accur
    0.15
    Activations Density 0.064%

    No Known Activations