© 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. 34811
    Prev
    Next
    INDEX
    Explanations

    these areas, individual, represented

    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
    /WebAPI
    -0.10
    ¶Į
    -0.10
    _ASSUME
    -0.08
     kaldır
    -0.08
    ODEV
    -0.08
    _Bar
    -0.07
    EMPLARY
    -0.07
    oop
    -0.07
    sob
    -0.07
    ãĨ
    -0.07
    POSITIVE LOGITS
    à¤Łà¤ķ
    0.08
     Baldwin
    0.07
    -)
    0.07
     %#
    0.07
    phem
    0.07
    çĸĹ
    0.07
    styleType
    0.07
    oka
    0.07
    -enable
    0.07
     splash
    0.07
    Activations Density 0.058%

    No Known Activations