© 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. 42043
    Prev
    Next
    INDEX
    Explanations

    ensuring that risks and issues

    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
     Sta
    -0.10
     inability
    -0.10
    aida
    -0.10
    umes
    -0.09
     Failure
    -0.09
    agi
    -0.09
     uncomp
    -0.09
    Failure
    -0.08
     failure
    -0.08
    ahi
    -0.08
    POSITIVE LOGITS
     problem
    0.16
     problems
    0.14
     goals
    0.14
     objectives
    0.13
     doors
    0.12
     problema
    0.12
     loose
    0.12
    éĹ®é¢ĺ
    0.12
     slate
    0.12
     wounds
    0.12
    Activations Density 0.146%

    No Known Activations