© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Llama3.3-70B-IT (Instruct)
    3. 50-RESID-POST-GF
    4. 34524
    Prev
    Next
    INDEX
    Explanations

    feedback request

    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
     Stock
    -0.09
     Haven
    -0.09
     Yup
    -0.09
     Gore
    -0.09
     Kee
    -0.08
     rejo
    -0.08
    ocs
    -0.08
     any
    -0.08
     Asset
    -0.08
    POSITIVE LOGITS
    no
    0.12
     wait
    0.12
     неÑĤ
    0.11
     no
    0.11
     Nope
    0.11
     Wait
    0.11
    No
    0.10
    Wait
    0.10
     ÐĿеÑĤ
    0.10
     NO
    0.10
    Activations Density 0.070%

    No Known Activations