© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 23591
    Prev
    Next
    INDEX
    Explanations

    front prom

    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
    åı
    -0.11
     hill
    -0.10
     hol
    -0.09
     courtyard
    -0.09
    agate
    -0.09
    elli
    -0.09
     Interior
    -0.09
     경기ëıĦ
    -0.09
    olean
    -0.09
     Brush
    -0.09
    POSITIVE LOGITS
     prom
    0.32
     Prom
    0.22
    prom
    0.20
    Prom
    0.16
    eprom
    0.16
    -prom
    0.16
    _prom
    0.14
     walk
    0.14
     strip
    0.14
    /prom
    0.13
    Activations Density 0.053%

    No Known Activations