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

    Neuronpedia

    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. 11-RESID-POST-AA
    11. 40963
    Prev
    Next
    INDEX
    Explanations

    poor

    np_max-act · gemini-2.0-flash

    The neuron activates on adjectives and phrases that describe severe or poor disease outcomes (e.g., “poor,” “dismal,” “aggressive,” “prognosis”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    合同
    -0.06
    /logout
    -0.06
     washed
    -0.06
     Wade
    -0.06
    skyt
    -0.06
     Rhode
    -0.06
    .findBy
    -0.06
    _widgets
    -0.06
     بخش
    -0.06
     Rosen
    -0.06
    POSITIVE LOGITS
    (tcp
    0.07
    يكا
    0.06
     mundane
    0.06
    _zero
    0.06
     cuer
    0.06
     popul
    0.06
     agre
    0.06
     decre
    0.06
     tremendously
    0.06
    _binary
    0.06
    Activations Density 0.033%

    No Known Activations