Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Llama3.3-70B-IT (Instruct)
    3. 50-RESID-POST-GF
    4. 65459
    Prev
    Next
    INDEX
    Explanations

    licenses, assessment, translator, investing

    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
    оÑĢд
    -0.10
     ï¿£
    -0.09
    abilia
    -0.08
    ijken
    -0.08
     dispos
    -0.08
    £¼
    -0.08
    gard
    -0.08
    EMPLARY
    -0.08
    .yang
    -0.08
     ún
    -0.08
    POSITIVE LOGITS
     animal
    0.12
     various
    0.10
    types
    0.10
    animal
    0.10
     da
    0.10
     Kore
    0.10
     types
    0.10
     human
    0.09
     Various
    0.09
     restaurant
    0.09
    Activations Density 0.412%

    No Known Activations