© 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. 8192
    Prev
    Next
    INDEX
    Explanations

    young age

    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
     Adult
    -0.12
    eri
    -0.11
    rang
    -0.10
     midnight
    -0.09
    ￣￣
    -0.08
    ï½Ĵ
    -0.08
    ëŀĮ
    -0.08
    å¤ķ
    -0.08
    Intialized
    -0.08
     witch
    -0.08
    POSITIVE LOGITS
     early
    0.62
    early
    0.53
    æĹ©
    0.47
     Early
    0.42
    Early
    0.42
     earliest
    0.35
     sỼm
    0.34
     young
    0.27
     erken
    0.25
     ÑĢан
    0.25
    Activations Density 0.157%

    No Known Activations