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. 65494
    Prev
    Next
    INDEX
    Explanations

    qualities of strength

    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
    rtle
    -0.09
     daring
    -0.09
    ãģĬãĤĬ
    -0.09
    abler
    -0.09
    oki
    -0.09
    ê·¹
    -0.09
    527
    -0.09
    аÑĢов
    -0.09
    gabe
    -0.08
    592
    -0.08
    POSITIVE LOGITS
     mẽ
    0.29
    holds
    0.24
    -strong
    0.16
    arm
    0.16
    sville
    0.16
    -arm
    0.14
     khá»ıe
    0.14
    bow
    0.14
    hold
    0.13
    arming
    0.13
    Activations Density 0.022%

    No Known Activations