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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Llama3.3-70B-IT (Instruct)
    3. 50-RESID-POST-GF
    4. 65264
    Prev
    Next
    INDEX
    Explanations

    comparing relative change next year

    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
    :.:
    -0.10
    oui
    -0.09
     Ley
    -0.09
    ï¾ī
    -0.09
     Patri
    -0.09
     raised
    -0.09
    å±Ģ
    -0.08
    kova
    -0.08
    onis
    -0.08
    XXXX
    -0.08
    POSITIVE LOGITS
     compared
    0.30
     Compared
    0.20
    comp
    0.16
     year
    0.15
     relative
    0.15
    RelativeTo
    0.13
     поÑĢÑĸв
    0.13
    (comp
    0.12
    pared
    0.12
     overall
    0.12
    Activations Density 0.052%

    No Known Activations