© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 30540
    Prev
    Next
    INDEX
    Explanations

    good and bad outcomes

    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
     ref
    -0.10
    ãĢĢãĥİ
    -0.09
    afone
    -0.09
    ino
    -0.09
     third
    -0.09
     increasing
    -0.08
    INO
    -0.08
     Peak
    -0.08
    /st
    -0.08
    EmptyEntries
    -0.08
    POSITIVE LOGITS
     moral
    0.20
     Moral
    0.19
     years
    0.15
     end
    0.14
     END
    0.12
    Years
    0.12
     morals
    0.12
     ends
    0.12
     morally
    0.12
     morale
    0.12
    Activations Density 0.021%

    No Known Activations