© 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. 18070
    Prev
    Next
    INDEX
    Explanations

    well- descriptive words

    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
    fully
    -0.10
     specially
    -0.09
    457
    -0.09
    NSNotificationCenter
    -0.09
    efully
    -0.09
    ÃŃsto
    -0.08
    ideographic
    -0.08
    ily
    -0.08
    ylland
    -0.08
     Meadows
    -0.08
    POSITIVE LOGITS
    ness
    0.19
    /-
    0.18
    /high
    0.16
    -out
    0.12
    NESS
    0.12
    /lic
    0.11
    /exec
    0.11
    /generated
    0.11
    -Out
    0.10
    ãĢģé«ĺ
    0.10
    Activations Density 0.066%

    No Known Activations