© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 25045
    Prev
    Next
    INDEX
    Explanations

    professions

    np_max-act · gemini-2.0-flash

    The neuron consistently activates on the token “Physician,” i.e. it detects occurrences of the word “Physician” (as in the “Requesting Physician” field).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    medical terminology and details related to patient information.

    oai_token-act-pair · gpt-4o-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
    álido
    -0.06
    _v
    -0.06
    (media
    -0.06
    creates
    -0.06
    flow
    -0.06
     Gloss
    -0.06
    ål
    -0.06
     vydání
    -0.06
     залеж
    -0.06
    いか
    -0.06
    POSITIVE LOGITS
     đâu
    0.07
    .ZERO
    0.06
    افظ
    0.06
    .Consumer
    0.06
    _exists
    0.06
    oise
    0.06
     Typography
    0.06
     owning
    0.06
     Omega
    0.06
     zengin
    0.06
    Activations Density 0.000%

    No Known Activations