© 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. 4396
    Prev
    Next
    INDEX
    Explanations

    likely to be chosen

    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
     admittedly
    -0.14
     evidently
    -0.12
    604
    -0.10
     abych
    -0.09
     supposedly
    -0.09
    ãģªãģ®
    -0.09
    ãĤĵãģ§ãģĻ
    -0.08
     Optionally
    -0.08
    působ
    -0.08
    ãģijãĤĮãģ©
    -0.08
    POSITIVE LOGITS
     probably
    0.60
     likely
    0.57
    probably
    0.44
    likely
    0.43
     Probably
    0.42
    Probably
    0.38
     probable
    0.35
     muht
    0.35
    åı¯èĥ½
    0.35
     веÑĢоÑıÑĤ
    0.33
    Activations Density 0.530%

    No Known Activations