© 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. 23883
    Prev
    Next
    INDEX
    Explanations

    verbs denoting 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
    ¶Į
    -0.10
    asiswa
    -0.09
    _constants
    -0.09
    ulton
    -0.09
    алоÑģÑı
    -0.09
    stp
    -0.09
    ambio
    -0.08
     thereof
    -0.08
    cimiento
    -0.08
    sembled
    -0.08
    POSITIVE LOGITS
    zyÄĩ
    0.12
    иÑĤÑĮ
    0.12
    ar
    0.12
    owaÄĩ
    0.11
    izzare
    0.11
    ÑĩиÑĤÑĮ
    0.11
    ваÑĤÑĮ
    0.11
    ando
    0.10
    é
    0.10
    ificar
    0.10
    Activations Density 0.116%

    No Known Activations