© 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. 9981
    Prev
    Next
    INDEX
    Explanations

    slang and informal greetings

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

    informal conversational language, particularly casual speech patterns and direct address to "you".

    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
     Fucking
    -0.13
     fucking
    -0.12
     FUCK
    -0.11
     guy
    -0.11
     guys
    -0.10
     belt
    -0.10
     asshole
    -0.10
     shitty
    -0.10
    belt
    -0.10
     inde
    -0.10
    POSITIVE LOGITS
    izzle
    0.15
    aight
    0.13
     fam
    0.13
     chill
    0.12
     props
    0.11
     legit
    0.11
     bro
    0.11
     crib
    0.10
    TRL
    0.10
     Fam
    0.10
    Activations Density 0.070%

    No Known Activations