© 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. 23425
    Prev
    Next
    INDEX
    Explanations

    list of some

    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
    HttpException
    -0.10
     annonces
    -0.10
     Lowest
    -0.10
     sond
    -0.08
    δί
    -0.08
    WithError
    -0.08
     predomin
    -0.08
    727
    -0.08
    lez
    -0.08
    imeo
    -0.08
    POSITIVE LOGITS
     major
    0.45
     popular
    0.42
    popular
    0.32
    major
    0.31
     Popular
    0.30
    Popular
    0.28
     попÑĥлÑıÑĢ
    0.28
     common
    0.26
     Major
    0.24
     주ìļĶ
    0.23
    Activations Density 0.319%

    No Known Activations