© 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. 24840
    Prev
    Next
    INDEX
    Explanations

    not existing

    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
    Intialized
    -0.10
    PostalCodes
    -0.10
     bear
    -0.09
    senal
    -0.09
    aurant
    -0.09
    urat
    -0.09
     Deborah
    -0.08
     dreaming
    -0.08
    .scalablytyped
    -0.08
     torpedo
    -0.08
    POSITIVE LOGITS
    æ¶Ī
    0.23
     existence
    0.18
     ce
    0.17
     иÑģÑĩ
    0.15
     Ce
    0.15
     ÑĢаÑģÑĤвоÑĢ
    0.15
     vapor
    0.15
    van
    0.15
    NotExist
    0.14
     destruction
    0.14
    Activations Density 0.098%

    No Known Activations