© 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. 4123
    Prev
    Next
    INDEX
    Explanations

    in some way

    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
    ersen
    -0.10
     anybody
    -0.09
     sometimes
    -0.09
    allback
    -0.09
     veces
    -0.09
     Several
    -0.08
    896
    -0.08
     Others
    -0.08
     ocas
    -0.08
    berra
    -0.08
    POSITIVE LOGITS
     some
    0.47
     somew
    0.44
    some
    0.39
     quelque
    0.38
     irgend
    0.38
     qualche
    0.38
     somewhere
    0.37
     algún
    0.36
     alguna
    0.33
     nÄĽjak
    0.33
    Activations Density 0.229%

    No Known Activations