© 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. 22543
    Prev
    Next
    INDEX
    Explanations

    summaries not factually consistent

    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
     tslint
    -0.10
     gut
    -0.09
    ffc
    -0.09
     genu
    -0.08
     widgets
    -0.08
    .Undef
    -0.08
    heimer
    -0.08
     Disorder
    -0.08
    PointerException
    -0.08
    èīĩ
    -0.08
    POSITIVE LOGITS
     halluc
    0.18
    å¿ł
    0.12
     fine
    0.11
    hall
    0.11
     factual
    0.11
     output
    0.10
     coverage
    0.10
     ver
    0.10
     reg
    0.10
     Hall
    0.10
    Activations Density 0.079%

    No Known Activations