© 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
    5. 50-RESID-POST-GF
    7. 37894
    Prev
    Next
    INDEX
    Explanations

    use, enumerating, exec

    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
     Conrad
    -0.10
    417
    -0.10
    ROLS
    -0.10
     nuest
    -0.09
    åĴ²
    -0.09
    aits
    -0.09
     Gong
    -0.08
    964
    -0.08
    linkplain
    -0.08
    ãĤº
    -0.08
    POSITIVE LOGITS
     use
    0.16
     `
    0.16
    使çĶ¨
    0.12
     uses
    0.12
    Iss
    0.12
    [`
    0.11
     Use
    0.11
     "`
    0.11
     gebruik
    0.11
     calls
    0.11
    Activations Density 0.183%

    No Known Activations