© 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. 37036
    Prev
    Next
    INDEX
    Explanations

    can be verb

    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
    CTL
    -0.10
    amas
    -0.09
    /as
    -0.09
    fak
    -0.09
    wich
    -0.09
    ich
    -0.08
     entreprene
    -0.08
    ixel
    -0.08
    shiv
    -0.08
    uda
    -0.08
    POSITIVE LOGITS
     done
    0.27
     include
    0.22
    done
    0.22
     includes
    0.20
     happen
    0.20
     happened
    0.20
     Done
    0.20
    Done
    0.19
     happens
    0.18
    -done
    0.17
    Activations Density 0.029%

    No Known Activations