© 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. 49656
    Prev
    Next
    INDEX
    Explanations

    tv show titles

    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
    756
    -0.09
    lage
    -0.09
     Feature
    -0.09
    urd
    -0.09
    /renderer
    -0.08
    .accessToken
    -0.08
     Choice
    -0.08
     THR
    -0.08
    rlen
    -0.08
     burgl
    -0.08
    POSITIVE LOGITS
    902
    0.17
    infeld
    0.16
     NC
    0.15
     Diagnosis
    0.15
     CSI
    0.14
     Dawson
    0.14
     Alias
    0.13
     ER
    0.13
     Hogan
    0.13
     Law
    0.12
    Activations Density 0.100%

    No Known Activations