© 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. 24431
    Prev
    Next
    INDEX
    Explanations

    counting numbers and sequences

    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
     Eis
    -0.09
     amounts
    -0.09
    536
    -0.08
     Wass
    -0.08
     Amount
    -0.08
    quent
    -0.08
     dipl
    -0.08
    èĸ¦
    -0.08
     Lyon
    -0.08
     punch
    -0.08
    POSITIVE LOGITS
    reet
    0.10
    amac
    0.08
     Levy
    0.08
    \Dependency
    0.08
    URY
    0.08
    eview
    0.08
    ì¡°
    0.08
    ofire
    0.08
     tail
    0.08
    âĺħâĺħ
    0.07
    Activations Density 0.026%

    No Known Activations