© 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
    5. 50-RESID-POST-GF
    7. 34765
    Prev
    Next
    INDEX
    Explanations

    to improve and creative works

    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
     ÃľNÄ°VERS
    -0.07
     ÃľNÄ°
    -0.07
    ï¾
    -0.06
    ÂŃi
    -0.06
    :\n
    -0.06
    ücret
    -0.06
     UsersController
    -0.06
     ...\n\n\n\n
    -0.06
    ':\n\n
    -0.06
     âĢ¦
    -0.06
    POSITIVE LOGITS
     nuest
    0.11
    ******č\n
    0.10
     zdrav
    0.09
    ÂĢÂĢ
    0.09
     tieten
    0.09
    ¶Į
    0.09
    ¦æĥħ
    0.08
    <|begin_of_text|>
    0.08
     имÑĥ
    0.08
     Bilg
    0.08
    Activations Density 1.550%

    No Known Activations