© 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. 33413
    Prev
    Next
    INDEX
    Explanations

    they fought with all their might

    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
    .reporting
    -0.09
    eral
    -0.09
    .between
    -0.09
     several
    -0.08
    beck
    -0.08
    g
    -0.08
     à¸ŀร
    -0.08
    isch
    -0.08
    igans
    -0.08
    RAY
    -0.08
    POSITIVE LOGITS
     highs
    0.11
    EMPLARY
    0.11
    æľīçļĦ
    0.10
     mountains
    0.09
     foreground
    0.09
     Mountains
    0.09
    evin
    0.09
    ë¶ĢíĦ°
    0.08
    PIP
    0.08
    umer
    0.08
    Activations Density 0.141%

    No Known Activations