© 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. 30155
    Prev
    Next
    INDEX
    Explanations

    some / similar 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
     tutte
    -0.10
     varias
    -0.09
    algo
    -0.09
     altre
    -0.09
    avana
    -0.09
     hvordan
    -0.08
    iras
    -0.08
     todas
    -0.08
    amo
    -0.08
    AGER
    -0.08
    POSITIVE LOGITS
     some
    0.71
     Some
    0.60
    some
    0.57
    Some
    0.54
    æľīäºĽ
    0.53
     некоÑĤоÑĢÑĭе
    0.46
    ä¸ĢäºĽ
    0.46
     bazı
    0.46
     некоÑĤоÑĢÑĭÑħ
    0.45
     SOME
    0.44
    Activations Density 0.246%

    No Known Activations