© 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. 51305
    Prev
    Next
    INDEX
    Explanations

    identify, recognize, detect

    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
     Spec
    -0.09
     Specialty
    -0.09
    zas
    -0.08
    bairro
    -0.08
     rational
    -0.08
    itten
    -0.08
    Defined
    -0.08
    ekler
    -0.08
     Doub
    -0.08
     misleading
    -0.08
    POSITIVE LOGITS
    è¯Ĩ
    0.20
     recognition
    0.19
     identification
    0.18
    èŃĺ
    0.18
     identify
    0.17
     recognize
    0.17
     Recognition
    0.16
    Recognition
    0.16
    Recogn
    0.15
     Identification
    0.15
    Activations Density 0.157%

    No Known Activations