© 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. 34278
    Prev
    Next
    INDEX
    Explanations

    states described by which

    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
     rằng
    -0.11
    619
    -0.10
    805
    -0.10
    classNames
    -0.10
    .metamodel
    -0.09
    unan
    -0.09
    irth
    -0.08
    icamente
    -0.08
    Ether
    -0.08
    âĢŀJ
    -0.08
    POSITIVE LOGITS
    soever
    0.28
    -ever
    0.16
     we
    0.13
    /how
    0.11
    (es
    0.10
     they
    0.10
    ž
    0.10
    s
    0.10
     behalf
    0.10
    ’;
    0.10
    Activations Density 0.047%

    No Known Activations