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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 15-RESID-POST-AA
    11. 6402
    Prev
    Next
    INDEX
    Explanations

    Grief and loss

    np_max-act · gemini-2.0-flash

    References to bereavement, grief, loss, or comforting/supportive language about death and mourning.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    조
    -0.07
     看
    -0.07
    گو
    -0.06
     Quý
    -0.06
     promised
    -0.06
    ckill
    -0.06
     BYU
    -0.06
     fun
    -0.06
    Select
    -0.06
    änger
    -0.06
    POSITIVE LOGITS
     eruption
    0.07
     gasoline
    0.07
    /remove
    0.07
    .AspNet
    0.07
    Shell
    0.06
    oblin
    0.06
    ()
↵
↵
↵
    0.06
     bottled
    0.06
    -business
    0.06
     restraining
    0.06
    Activations Density 0.126%

    No Known Activations