© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 28996
    Prev
    Next
    INDEX
    Explanations

    points and steps

    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
    ÐIJÑĢÑħÑĸв
    -0.11
    681
    -0.09
     hor
    -0.08
     FE
    -0.08
     gr
    -0.08
     on
    -0.08
    !\n\n\n\n\n\n
    -0.08
     ME
    -0.08
    _separator
    -0.08
     пеÑĢеÑĤ
    -0.08
    POSITIVE LOGITS
    igs
    0.08
    IGHL
    0.08
    seealso
    0.08
     Morm
    0.08
    ¶Į
    0.07
    äºĭåĭĻ
    0.07
    ursed
    0.07
    ä¹Ĥ
    0.07
    imeo
    0.07
    383
    0.07
    Activations Density 0.446%

    No Known Activations