© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 1348
    Prev
    Next
    INDEX
    Explanations

    distance after determiners

    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
    isle
    -0.09
    achable
    -0.09
    oux
    -0.09
     stead
    -0.09
    quent
    -0.08
     Disconnect
    -0.08
    Dia
    -0.08
    _DELETED
    -0.08
    itore
    -0.08
    ãĢĥ
    -0.08
    POSITIVE LOGITS
     distance
    0.70
    distance
    0.54
     Distance
    0.53
     distances
    0.52
    Distance
    0.48
    è·Ŀ离
    0.47
    _distance
    0.45
     distancia
    0.45
    è·ĿéĽ¢
    0.44
     ÑĢаÑģÑģÑĤоÑı
    0.44
    Activations Density 0.101%

    No Known Activations