© 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. 13134
    Prev
    Next
    INDEX
    Explanations

    times for activities

    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
     early
    -0.13
     Early
    -0.11
    early
    -0.11
     daytime
    -0.10
     sunrise
    -0.10
    Early
    -0.10
    28
    -0.09
     Tos
    -0.09
    22
    -0.09
    41
    -0.09
    POSITIVE LOGITS
    pm
    0.10
    åĤ
    0.10
     Barnett
    0.10
     pm
    0.10
    430
    0.10
    opc
    0.09
     !:
    0.09
     depress
    0.09
     PM
    0.09
     AM
    0.09
    Activations Density 0.032%

    No Known Activations