© 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. 58313
    Prev
    Next
    INDEX
    Explanations

    oma

    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
     severe
    -0.10
     stem
    -0.09
     battles
    -0.09
     drib
    -0.09
     steep
    -0.09
     Cel
    -0.09
     tape
    -0.09
    Severity
    -0.09
     ephem
    -0.09
    gv
    -0.09
    POSITIVE LOGITS
     masses
    0.20
     growth
    0.16
     mass
    0.16
     benign
    0.16
    ben
    0.16
    grow
    0.15
    oma
    0.14
     Ben
    0.14
    growth
    0.13
    omas
    0.13
    Activations Density 0.057%

    No Known Activations