© 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. 2859
    Prev
    Next
    INDEX
    Explanations

    connecting positive attributes

    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
     responsiveness
    -0.12
    .scalablytyped
    -0.10
    GBK
    -0.09
     geil
    -0.09
    atty
    -0.08
    .Requires
    -0.08
    lef
    -0.08
    ixin
    -0.08
    <typeof
    -0.08
     verbosity
    -0.08
    POSITIVE LOGITS
     safety
    0.19
     standards
    0.16
    å®īåħ¨
    0.14
     Safety
    0.13
     Standards
    0.13
     performance
    0.13
    Safety
    0.13
     repe
    0.13
     consistency
    0.12
     security
    0.12
    Activations Density 0.006%

    No Known Activations