© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 22005
    Prev
    Next
    INDEX
    Explanations

    right direction, location, actions

    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
     smack
    -0.13
    orest
    -0.10
    ioni
    -0.10
    hdr
    -0.10
    riel
    -0.09
     left
    -0.09
    azon
    -0.09
    Äı
    -0.09
    ese
    -0.09
    adi
    -0.09
    POSITIVE LOGITS
    -hand
    0.22
    ward
    0.22
    most
    0.20
    eous
    0.19
    ToLeft
    0.19
    -click
    0.15
    wards
    0.15
    -wing
    0.14
     hand
    0.14
    ัà¸į
    0.13
    Activations Density 0.023%

    No Known Activations