© 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. 63450
    Prev
    Next
    INDEX
    Explanations

    preceding verbs with nouns/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
    ebek
    -0.08
    rob
    -0.08
    sto
    -0.08
    dde
    -0.08
    845
    -0.08
     Lobby
    -0.08
    assa
    -0.08
    ought
    -0.08
     Moran
    -0.08
    ((((
    -0.07
    POSITIVE LOGITS
    æıIJä¾Ľ
    0.11
    åıijåĩº
    0.11
     provide
    0.10
    лиÑĪком
    0.10
     give
    0.09
     making
    0.09
    è¿Ľè¡Į
    0.09
     provides
    0.09
     gives
    0.09
    ziel
    0.08
    Activations Density 0.617%

    No Known Activations