© 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. 37986
    Prev
    Next
    INDEX
    Explanations

    commands, satisfaction, technology, networks, examples, descriptions, subject, innovations, form, RPG

    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
    ssel
    -0.09
     McCarthy
    -0.09
    Å¡ek
    -0.08
    opak
    -0.08
    łéĻ¤
    -0.08
     baģlantılar
    -0.08
    agram
    -0.08
    afort
    -0.08
     ÅŁekl
    -0.08
    Å¡lo
    -0.08
    POSITIVE LOGITS
     Feld
    0.10
    .metamodel
    0.09
    âĢ¦"\n\n
    0.09
     Fulton
    0.08
    .Axis
    0.08
     _______,
    0.08
    ble
    0.08
    ault
    0.08
    381
    0.08
    ulton
    0.08
    Activations Density 0.044%

    No Known Activations