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. 44988
    Prev
    Next
    INDEX
    Explanations

    a [descriptor]

    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
     hallmark
    -0.10
     greatest
    -0.09
     Friendship
    -0.09
    steller
    -0.09
     certain
    -0.09
     Gast
    -0.09
    _hostname
    -0.08
    body
    -0.08
    atical
    -0.08
    uld
    -0.08
    POSITIVE LOGITS
    los
    0.15
     popular
    0.14
     part
    0.13
    verse
    0.12
    éĩįè¦ģ
    0.12
    plied
    0.11
     wicht
    0.11
     member
    0.11
     important
    0.11
     ÑĩаÑģÑĤÑĮ
    0.11
    Activations Density 0.116%

    No Known Activations