© 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. 38141
    Prev
    Next
    INDEX
    Explanations

    structured data fields

    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
    andro
    -0.10
    ioni
    -0.10
     Matth
    -0.10
    fcn
    -0.10
     watering
    -0.10
     sectarian
    -0.09
     fkk
    -0.09
     XPAR
    -0.09
     LGPL
    -0.08
    swire
    -0.08
    POSITIVE LOGITS
     Cors
    0.10
     Blades
    0.09
    ￣￣￣
    0.09
     VR
    0.09
    usters
    0.09
     Phys
    0.09
    ocz
    0.09
     Pavilion
    0.09
     Bulld
    0.09
    vide
    0.09
    Activations Density 0.006%

    No Known Activations