© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 24258
    Prev
    Next
    INDEX
    Explanations

    dialogue

    np_max-act · gemini-2.0-flash

    casual dialogue turn-openers and chatty questions (e.g., “Hey,” “what’s up?”) in conversational exchanges.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Landscape
    -0.07
     paginator
    -0.07
     béné
    -0.07
     binding
    -0.06
    -assets
    -0.06
     différentes
    -0.06
    CommandLine
    -0.06
    datetime
    -0.06
    atsapp
    -0.06
    Outcome
    -0.06
    POSITIVE LOGITS
    _NE
    0.07
    花
    0.07
    mousemove
    0.06
    Come
    0.06
    ्शन
    0.06
    formik
    0.06
     завтра
    0.06
    �
    0.06
    Suddenly
    0.06
    findById
    0.06
    Activations Density 0.127%

    No Known Activations