© 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. 43405
    Prev
    Next
    INDEX
    Explanations

    have been chosen

    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
    annel
    -0.10
    æĥ³åĪ°
    -0.10
     Grat
    -0.09
     /.
    -0.09
    acman
    -0.09
     Resolve
    -0.09
     stor
    -0.09
    PCS
    -0.09
     Fowler
    -0.08
    685
    -0.08
    POSITIVE LOGITS
     been
    0.10
    331
    0.09
    been
    0.09
     need
    0.09
    624
    0.09
     loneliness
    0.09
    AuthGuard
    0.09
     proposition
    0.09
    _Selected
    0.09
     monitoring
    0.08
    Activations Density 0.046%

    No Known Activations