© 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. 23124
    Prev
    Next
    INDEX
    Explanations

    cause and effect actions

    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
     Podesta
    -0.10
    odes
    -0.09
    826
    -0.08
    leo
    -0.08
     Eugene
    -0.08
     Butt
    -0.08
    ONA
    -0.08
     Holl
    -0.08
    848
    -0.08
    cxx
    -0.08
    POSITIVE LOGITS
    使
    0.21
     khiến
    0.19
     makes
    0.17
     membuat
    0.16
    ï¼Į使
    0.16
    让æĪij
    0.15
     make
    0.15
    è®ĵ
    0.13
    à¸Ĺำà¹ĥห
    0.13
     making
    0.13
    Activations Density 0.110%

    No Known Activations