© 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. 13112
    Prev
    Next
    INDEX
    Explanations

    legitimate use cases

    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
    -inverse
    -0.09
     tac
    -0.09
    /em
    -0.08
     raw
    -0.08
     apprec
    -0.08
    iland
    -0.08
     nonzero
    -0.08
     Comfort
    -0.08
    raw
    -0.08
    å°ĸ
    -0.08
    POSITIVE LOGITS
     innocent
    0.50
     innoc
    0.48
     Innoc
    0.41
     harmless
    0.38
     legitimate
    0.37
     innocence
    0.34
     benign
    0.34
     normal
    0.33
    æŃ£å¸¸
    0.30
     legit
    0.29
    Activations Density 0.280%

    No Known Activations