© 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. 3896
    Prev
    Next
    INDEX
    Explanations

    that this

    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
    äch
    -0.08
    vern
    -0.08
    ayd
    -0.08
    achu
    -0.07
    CORD
    -0.07
     ëĭ¹
    -0.07
    ForMember
    -0.07
    comed
    -0.07
     attempts
    -0.07
    rig
    -0.07
    POSITIVE LOGITS
     this
    0.29
    this
    0.26
    è¿Ļ
    0.21
    è¿Ļ个
    0.20
    \tthis
    0.20
     nÃły
    0.19
     This
    0.19
     اÛĮÙĨ
    0.19
    è¿Ļç§į
    0.18
    This
    0.18
    Activations Density 0.061%

    No Known Activations