© 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. 62313
    Prev
    Next
    INDEX
    Explanations

    subject followed by 'is', 'has', or 'pays'

    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
    _DSP
    -0.09
    .Payload
    -0.09
    emey
    -0.09
    inski
    -0.09
    apult
    -0.08
    velop
    -0.08
    заб
    -0.08
    quina
    -0.08
    quine
    -0.08
    undle
    -0.08
    POSITIVE LOGITS
     also
    0.22
    also
    0.18
     cũng
    0.16
     ÑĤакже
    0.16
     Also
    0.15
     juga
    0.14
     ÙĩÙħÚĨÙĨÛĮÙĨ
    0.14
    Also
    0.14
     también
    0.14
     também
    0.14
    Activations Density 0.014%

    No Known Activations