© 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. 54722
    Prev
    Next
    INDEX
    Explanations

    they are, they had, they want

    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
    859
    -0.10
    ãĥ³ãĤ¿
    -0.10
     ourselves
    -0.09
    rix
    -0.09
    _pas
    -0.09
    icina
    -0.09
    alles
    -0.09
    åĻ
    -0.09
     deem
    -0.08
    _VF
    -0.08
    POSITIVE LOGITS
     themselves
    0.22
    re
    0.21
    atically
    0.19
    're
    0.19
    ’;re
    0.18
    /us
    0.17
    /we
    0.15
    ÅĽmy
    0.13
    ï¼Įä»ĸ们
    0.12
    've
    0.11
    Activations Density 0.111%

    No Known Activations