© 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. 22545
    Prev
    Next
    INDEX
    Explanations

    connecting descriptive phrases

    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
     BoxFit
    -0.09
    uku
    -0.09
    ioni
    -0.09
     nackte
    -0.08
    ennen
    -0.08
    arih
    -0.08
    ebin
    -0.08
    .Singleton
    -0.08
     STDMETHODCALLTYPE
    -0.08
    olle
    -0.08
    POSITIVE LOGITS
    aminer
    0.09
     somewhat
    0.08
     conc
    0.08
    AGR
    0.08
     impro
    0.08
    ULD
    0.08
    essor
    0.08
    ttp
    0.08
    )const
    0.08
     âĶĢ
    0.08
    Activations Density 0.080%

    No Known Activations