© 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. 52164
    Prev
    Next
    INDEX
    Explanations

    can be used to

    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
    imuth
    -0.08
    907
    -0.08
    ector
    -0.08
     pÅĻitom
    -0.08
     letzten
    -0.07
    naz
    -0.07
    \č\n
    -0.07
    ouden
    -0.07
    loh
    -0.07
    Å¡en
    -0.07
    POSITIVE LOGITS
     another
    0.14
     again
    0.14
     dit
    0.13
     similar
    0.12
     also
    0.12
     ebenfalls
    0.12
    dit
    0.12
    another
    0.12
    again
    0.11
     yine
    0.11
    Activations Density 0.252%

    No Known Activations