© 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. 26497
    Prev
    Next
    INDEX
    Explanations

    You are right

    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
    mgr
    -0.09
    isay
    -0.09
    ä¸įäºĨ
    -0.09
    ofday
    -0.09
    enga
    -0.08
     wrongful
    -0.08
     Edmund
    -0.08
    หว
    -0.08
     Mare
    -0.08
     Wrong
    -0.08
    POSITIVE LOGITS
     right
    0.23
    right
    0.18
     correct
    0.18
     RIGHT
    0.15
    -right
    0.14
     Äijúng
    0.14
     Right
    0.13
    åı³
    0.13
    RIGHT
    0.13
    _right
    0.13
    Activations Density 0.009%

    No Known Activations