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. 65476
    Prev
    Next
    INDEX
    Explanations

    clauses explaining states or reasons

    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
    ¶Į
    -0.11
    usk
    -0.09
     mesmer
    -0.09
    Bias
    -0.09
     Pav
    -0.09
    lya
    -0.08
    'gc
    -0.08
    vore
    -0.08
     hassle
    -0.08
    egis
    -0.08
    POSITIVE LOGITS
    -Allow
    0.12
     ener
    0.12
     manufact
    0.09
     emailAddress
    0.09
     domic
    0.09
    Projection
    0.08
    ï¿
    0.08
     future
    0.08
     SMP
    0.08
     Toxic
    0.08
    Activations Density 0.047%

    No Known Activations