© 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. 3312
    Prev
    Next
    INDEX
    Explanations

    explore ways in literature techniques

    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
    rech
    -0.10
    perature
    -0.10
    éªĮ
    -0.09
    soever
    -0.09
    796
    -0.09
    tings
    -0.09
    esk
    -0.09
    ãģ¾ãģ¾
    -0.08
    deme
    -0.08
    мен
    -0.08
    POSITIVE LOGITS
    iture
    0.12
    atory
    0.12
     ways
    0.11
    AINED
    0.11
    ä¸Ģä¸ĭ
    0.10
    /exp
    0.10
    è¨İ
    0.10
     Further
    0.09
    erd
    0.09
    iners
    0.09
    Activations Density 0.022%

    No Known Activations