© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT (Instruct)
    5. 50-RESID-POST-GF
    7. 34054
    Prev
    Next
    INDEX
    Explanations

    i am humano and u r dog

    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
    .Contracts
    -0.10
    วรรà¸ĵ
    -0.08
     sist
    -0.08
     Speedway
    -0.08
    ady
    -0.08
    eacher
    -0.07
     ...\n\n\n\n
    -0.07
    elles
    -0.07
    fter
    -0.07
     INCIDENTAL
    -0.07
    POSITIVE LOGITS
     myself
    0.10
    iceps
    0.09
     quadr
    0.09
     maybe
    0.09
    irket
    0.09
     Machine
    0.08
    #
    0.08
     darn
    0.08
     humans
    0.08
     thought
    0.08
    Activations Density 0.036%

    No Known Activations