© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 35120
    Prev
    Next
    INDEX
    Explanations

    for each new shell session

    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
     ãģı
    -0.11
     Stre
    -0.10
    elik
    -0.10
     Perl
    -0.10
    ãĢĢï¾Ĭ
    -0.09
     Lap
    -0.09
     Cruise
    -0.09
    ckill
    -0.09
    omain
    -0.09
     Petty
    -0.09
    POSITIVE LOGITS
     shell
    0.19
     shells
    0.16
     Shell
    0.16
    /bash
    0.15
     ~/.
    0.14
     bash
    0.14
     Bash
    0.14
    shell
    0.14
    Shell
    0.13
    .profile
    0.13
    Activations Density 0.062%

    No Known Activations