© 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
    2. Llama3.3-70B-IT
    3. 50-RESID-POST-GF
    4. 45429
    Prev
    Next
    INDEX
    Explanations

    beat down

    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
    eer
    -0.11
    ic
    -0.10
    edium
    -0.09
    658
    -0.09
    hub
    -0.09
    ضÙħ
    -0.09
    er
    -0.09
    962
    -0.09
    hed
    -0.09
    gren
    -0.09
    POSITIVE LOGITS
    iful
    0.25
    rice
    0.20
    itudes
    0.19
    nik
    0.18
    ific
    0.18
     beat
    0.16
    riz
    0.16
     Beat
    0.16
    down
    0.15
    itude
    0.15
    Activations Density 0.021%

    No Known Activations