© 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. 36279
    Prev
    Next
    INDEX
    Explanations

    had always been

    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
    anan
    -0.09
     EITHER
    -0.09
    487
    -0.09
    orde
    -0.09
    718
    -0.09
    ennifer
    -0.09
    ardu
    -0.08
     Annex
    -0.08
     grop
    -0.08
    .obtain
    -0.08
    POSITIVE LOGITS
     never
    0.22
    never
    0.19
    nt
    0.17
     always
    0.17
     expected
    0.15
     Never
    0.15
    Never
    0.14
     никогда
    0.14
     nunca
    0.14
     heard
    0.14
    Activations Density 0.024%

    No Known Activations