© 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. 2624
    Prev
    Next
    INDEX
    Explanations

    showing an example of

    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
    oga
    -0.11
    imit
    -0.10
    åĿĬ
    -0.10
     samples
    -0.10
    _examples
    -0.09
    _example
    -0.09
    samples
    -0.09
    iable
    -0.09
     kterou
    -0.09
    amples
    -0.09
    POSITIVE LOGITS
    ãģĪãģ°
    0.13
     of
    0.11
     foremost
    0.10
     offsetof
    0.10
     usage
    0.09
     shows
    0.09
    /tutorial
    0.09
     иÑģполÑĮзованиÑı
    0.09
     application
    0.08
     taken
    0.08
    Activations Density 0.040%

    No Known Activations