© 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. 14060
    Prev
    Next
    INDEX
    Explanations

    hyperparameter tuning

    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
    ener
    -0.08
     polar
    -0.08
    .eof
    -0.08
    eof
    -0.08
    &s
    -0.08
    OK
    -0.08
     Orient
    -0.08
     Haut
    -0.08
     logic
    -0.08
     letters
    -0.08
    POSITIVE LOGITS
     tuning
    0.20
     Tun
    0.18
     hyper
    0.18
     tune
    0.17
    _TUN
    0.17
     tunes
    0.16
     tun
    0.15
     tuner
    0.14
     Tune
    0.14
     tuned
    0.14
    Activations Density 0.030%

    No Known Activations