© 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. 36692
    Prev
    Next
    INDEX
    Explanations

    establish and related concepts

    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
    fully
    -0.11
    fulness
    -0.10
    uality
    -0.10
    ation
    -0.09
    IfExists
    -0.09
     Zap
    -0.09
    d
    -0.09
    αÏĤ
    -0.09
     mek
    -0.09
     inclus
    -0.09
    POSITIVE LOGITS
    ishment
    0.16
    cer
    0.14
    ished
    0.13
    cimiento
    0.13
    ablish
    0.13
    ishments
    0.13
    ishing
    0.12
    isse
    0.12
    ãĥ¡ãĥ³ãĥĪ
    0.12
    issement
    0.12
    Activations Density 0.016%

    No Known Activations