© 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. 36690
    Prev
    Next
    INDEX
    Explanations

    numbers and words immediately following

    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
    ))*(
    -0.09
    711
    -0.09
     quot
    -0.08
    ÐIJÑĢÑħÑĸв
    -0.08
     odbor
    -0.08
    VC
    -0.08
    ARRANT
    -0.08
    tsy
    -0.08
     Barg
    -0.07
    ãĥĩãĥ«
    -0.07
    POSITIVE LOGITS
    boxed
    0.09
    allis
    0.09
    çļĦæĺ¯
    0.08
     indeed
    0.08
     hod
    0.08
     Bod
    0.08
     Peters
    0.08
    /do
    0.08
     =
    0.08
     originally
    0.08
    Activations Density 0.040%

    No Known Activations