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. 65512
    Prev
    Next
    INDEX
    Explanations

    with this landfill

    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
     boring
    -0.10
     improper
    -0.10
    OT
    -0.09
     malformed
    -0.09
    inium
    -0.09
     vicious
    -0.09
     fucked
    -0.08
     spot
    -0.08
     Consulting
    -0.08
     Ari
    -0.08
    POSITIVE LOGITS
    æķ·
    0.15
     customer
    0.12
     promises
    0.12
    æĢģ
    0.11
     promised
    0.11
    æħĭ
    0.11
     company
    0.11
     attitude
    0.11
     representatives
    0.10
     unwilling
    0.10
    Activations Density 0.142%

    No Known Activations