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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT (Instruct)
    5. 50-RESID-POST-GF
    7. 38564
    Prev
    Next
    INDEX
    Explanations

    exist solely

    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
    ils
    -0.11
    iko
    -0.10
     directly
    -0.10
     direct
    -0.09
     indirect
    -0.09
    apro
    -0.09
     ucfirst
    -0.08
    ostel
    -0.08
     loose
    -0.08
    nts
    -0.08
    POSITIVE LOGITS
     Äijá»ĥ
    0.13
    为äºĨ
    0.12
    à¹Įà¹Ģà¸ŀ
    0.11
    à¹Ģà¸ŀ
    0.10
     ÑĩÑĤобÑĭ
    0.10
    ultiply
    0.10
    Purpose
    0.10
    sole
    0.09
     ЧÑĤобÑĭ
    0.09
     inorder
    0.09
    Activations Density 0.030%

    No Known Activations