© 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. 17768
    Prev
    Next
    INDEX
    Explanations

    ha laughs

    np_acts-logits-general · gemini-2.5-flash-lite

    conversational or informal transitional phrases and hedging language.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @yooniel31
    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
     :/
    -0.11
     :|
    -0.11
    lix
    -0.10
     âĿ¤
    -0.10
    owie
    -0.09
    UTES
    -0.09
    ;:
    -0.09
     ðŁij
    -0.09
     ë¸
    -0.09
    UNCH
    -0.09
    POSITIVE LOGITS
     ha
    0.25
     Ha
    0.21
    laughs
    0.20
    Ha
    0.20
     HA
    0.19
    ha
    0.19
    åĵĪ
    0.19
    ahaha
    0.18
    HA
    0.16
    ï¼Īç¬ij
    0.16
    Activations Density 0.320%

    No Known Activations