© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 18608
    Prev
    Next
    INDEX
    Explanations

    years, industry, remember, caregivers

    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
    Negative Logits
    ckså
    -0.10
    ï¼Įæ¯Ķ
    -0.08
    기ëıĦ
    -0.08
    .\n
    -0.08
    çĶ
    -0.08
     jab
    -0.08
    Ｏ
    -0.08
    ishes
    -0.08
    <|begin_of_text|>
    -0.08
    :
    -0.07
    POSITIVE LOGITS
     ведÑĮ
    0.09
    vironment
    0.08
     maiden
    0.08
    (Photo
    0.08
    Ðħ
    0.08
    Ðİ
    0.08
     ©
    0.08
    ála
    0.08
     merupakan
    0.08
     Demir
    0.07
    Activations Density 0.338%

    No Known Activations