© 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. 51199
    Prev
    Next
    INDEX
    Explanations

    software tools and platforms

    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
    ména
    -0.09
    unately
    -0.09
    cores
    -0.09
    avax
    -0.09
    resher
    -0.08
    ç¯Ģ
    -0.08
    ackers
    -0.08
    IFn
    -0.08
     such
    -0.08
    imuth
    -0.08
    POSITIVE LOGITS
     lets
    0.12
     allows
    0.11
    allow
    0.11
     acquisitions
    0.11
     ideal
    0.11
    ideal
    0.10
     acquired
    0.10
    lett
    0.10
     pred
    0.10
     allow
    0.10
    Activations Density 0.068%

    No Known Activations