© 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. 56727
    Prev
    Next
    INDEX
    Explanations

    my self

    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
    âĦĸâĦĸ
    -0.09
    ((&
    -0.09
     ÑĤабли
    -0.09
     Ä°mpar
    -0.09
    872
    -0.08
    /*č\n
    -0.08
     âĹij
    -0.08
    _atual
    -0.08
     докÑĥм
    -0.08
    akra
    -0.08
    POSITIVE LOGITS
    (sp
    0.22
    ÌĨ
    0.22
     [_
    0.20
     ​​
    0.16
    Ìģ
    0.15
    [s
    0.13
    ÌĪ
    0.12
    ãĤ
    0.10
    Ì
    0.09
    ogh
    0.09
    Activations Density 0.164%

    No Known Activations