© 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
    2. Llama3.3-70B-IT (Instruct)
    3. 50-RESID-POST-GF
    4. 34100
    Prev
    Next
    INDEX
    Explanations

    necesitar and its conjugations

    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
    ers
    -0.13
    t
    -0.12
    uição
    -0.11
    e
    -0.11
    oux
    -0.10
    ابط
    -0.10
    tv
    -0.10
    ings
    -0.10
    cle
    -0.10
    sass
    -0.09
    POSITIVE LOGITS
    iona
    0.16
    ión
    0.13
    itar
    0.12
    iones
    0.12
    sthrough
    0.11
    itas
    0.10
    ION
    0.10
     Seas
    0.10
    моÑĤÑĢÑı
    0.10
    itag
    0.10
    Activations Density 0.037%

    No Known Activations