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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 37127
    Prev
    Next
    INDEX
    Explanations

    verbs followed by states or outcomes

    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
     itself
    -0.26
     its
    -0.12
    áno
    -0.12
     коÑĤоÑĢое
    -0.11
    ÑĪло
    -0.10
    /is
    -0.10
    å®ĥ
    -0.10
    įng
    -0.10
    <|begin_of_text|>
    -0.10
    ¶Į
    -0.09
    POSITIVE LOGITS
     themselves
    0.34
     коÑĤоÑĢÑĭе
    0.22
     thems
    0.19
     are
    0.17
     ones
    0.17
     denen
    0.16
    plural
    0.16
     aren
    0.15
    "They
    0.15
     oldukları
    0.14
    Activations Density 0.566%

    No Known Activations