© 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. 49195
    Prev
    Next
    INDEX
    Explanations

    degree of abstraction and specificity

    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
     incarn
    -0.10
     unprotected
    -0.10
     Fisher
    -0.09
    odata
    -0.09
     Freak
    -0.09
     Rodgers
    -0.09
     compass
    -0.09
    apes
    -0.09
    åłĤ
    -0.09
     Carn
    -0.09
    POSITIVE LOGITS
     Plot
    0.18
    Pl
    0.15
     Pl
    0.15
     Py
    0.15
    Plot
    0.15
     Nous
    0.14
     Parm
    0.14
     Intel
    0.12
     плаÑĤ
    0.12
    Py
    0.12
    Activations Density 0.038%

    No Known Activations