© 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. 39632
    Prev
    Next
    INDEX
    Explanations

    how to make or discuss

    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
    ahoo
    -0.10
     Sue
    -0.08
    \<
    -0.08
    536
    -0.08
     Uns
    -0.08
     Kore
    -0.08
    783
    -0.08
    iram
    -0.08
     Duty
    -0.08
     Sabb
    -0.08
    POSITIVE LOGITS
     instead
    0.14
     ways
    0.13
     general
    0.13
     legitimate
    0.13
     alternative
    0.12
     alternatives
    0.12
     Altern
    0.11
     how
    0.11
     Instead
    0.11
    altern
    0.10
    Activations Density 0.114%

    No Known Activations