© 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. 43215
    Prev
    Next
    INDEX
    Explanations

    noun following article

    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
     maneu
    -0.09
     intox
    -0.07
     поба
    -0.07
    ORMAT
    -0.07
    _contin
    -0.07
     guarante
    -0.07
     nowrap
    -0.07
    OLEAN
    -0.06
     ê°¤ë¡ľê·¸ë¡ľ
    -0.06
     Marie
    -0.06
    POSITIVE LOGITS
    ¶Į
    0.10
     tzv
    0.10
    įng
    0.08
    ï¼Īå¹³æĪIJ
    0.08
    Ðĭ
    0.08
     -*-č\n
    0.08
    .Dictionary
    0.08
    ÐIJÑĢÑħÑĸв
    0.07
     siguientes
    0.07
    .Formatter
    0.07
    Activations Density 0.452%

    No Known Activations