© 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. 3543
    Prev
    Next
    INDEX
    Explanations

    actually, actually, actually

    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
     otherwise
    -0.10
     previously
    -0.09
    once
    -0.09
     once
    -0.09
    haps
    -0.08
    Without
    -0.08
    oba
    -0.08
     aforementioned
    -0.08
     Without
    -0.08
    aph
    -0.08
    POSITIVE LOGITS
     actually
    0.20
    ä¸įæĺ¯
    0.17
     although
    0.17
     aslında
    0.17
     Actually
    0.17
    Actually
    0.17
    ãģ§ãģ¯ãģªãģı
    0.17
     eigentlich
    0.17
    actually
    0.16
     नह
    0.15
    Activations Density 1.043%

    No Known Activations