© 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. 13119
    Prev
    Next
    INDEX
    Explanations

    negative aspects and limitations

    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
     inconsistency
    -0.16
     inconsistencies
    -0.13
     inconsistent
    -0.13
     improperly
    -0.09
     Injury
    -0.09
     Difficulty
    -0.09
     setback
    -0.09
     incompetence
    -0.09
     incompetent
    -0.09
     genu
    -0.09
    POSITIVE LOGITS
     flaw
    0.31
     fault
    0.28
     flaws
    0.26
     fail
    0.25
     problems
    0.25
     weakness
    0.24
     weaknesses
    0.23
    fault
    0.23
     defects
    0.22
     defect
    0.21
    Activations Density 0.147%

    No Known Activations