© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 63662
    Prev
    Next
    INDEX
    Explanations

    importance, value, dangers, benefits

    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
    iao
    -0.10
    illez
    -0.09
     Fra
    -0.09
     Fr
    -0.08
    oj
    -0.08
    åį¢
    -0.08
    lis
    -0.08
    åģ¥
    -0.08
    auen
    -0.08
    eco
    -0.08
    POSITIVE LOGITS
     importance
    0.58
     Importance
    0.43
     IMPORT
    0.27
     value
    0.26
    import
    0.26
     benefits
    0.25
     benefit
    0.25
     necessity
    0.24
     need
    0.23
    Import
    0.23
    Activations Density 0.074%

    No Known Activations