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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Llama3.3-70B-IT (Instruct)
    3. 50-RESID-POST-GF
    4. 65036
    Prev
    Next
    INDEX
    Explanations

    list items

    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
    [email
    -0.16
     gl
    -0.11
     [
    -0.11
     Gl
    -0.10
    angan
    -0.09
     un
    -0.09
     port
    -0.09
     po
    -0.09
     Part
    -0.09
     X
    -0.09
    POSITIVE LOGITS
    ä¸ĭ载次æķ°
    0.11
    ngo
    0.09
     detain
    0.09
    çĽijåIJ¬é¡µéĿ¢
    0.09
    ÑıÑĩ
    0.09
     garner
    0.09
    shortcode
    0.09
    ãģ£ãģį
    0.08
     {.
    0.08
    éĺħ读次æķ°
    0.08
    Activations Density 0.078%

    No Known Activations