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. 45029
    Prev
    Next
    INDEX
    Explanations

    humanity's state or future

    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
    rew
    -0.11
     humanoid
    -0.10
     GOODMAN
    -0.09
    \tCopyright
    -0.09
    indi
    -0.09
    hips
    -0.09
    icer
    -0.09
     ấy
    -0.09
    ivia
    -0.08
     Äijá»Ŀi
    -0.08
    POSITIVE LOGITS
     beings
    0.15
    oids
    0.14
     itself
    0.14
    -kind
    0.11
    ankind
    0.11
     writ
    0.10
    eness
    0.10
    ataka
    0.10
    âĢĮØ´ÙĨ
    0.09
     جÙħع
    0.09
    Activations Density 0.030%

    No Known Activations