© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 22010
    Prev
    Next
    INDEX
    Explanations

    and/or conjunctions leading to research

    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
    izioni
    -0.09
     vign
    -0.09
    è¿Ľè¡Į
    -0.09
    fdc
    -0.09
     aud
    -0.08
    otions
    -0.08
     duplic
    -0.08
    nech
    -0.08
     interrog
    -0.08
    onga
    -0.08
    POSITIVE LOGITS
    /or
    0.16
     debate
    0.12
     analysis
    0.12
     investigation
    0.11
     contempl
    0.10
     recreation
    0.10
     ado
    0.10
     discussion
    0.10
     attempted
    0.10
     eventual
    0.09
    Activations Density 0.098%

    No Known Activations