© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 91922
    Prev
    Next
    INDEX
    Explanations

    awareness of diseases

    np_max-act · gemini-2.0-flash

    The neuron activates on language describing shortfalls in mental‐health understanding or support—terms like “stigma,” “lack,” “education,” and “subject” when discussing gaps in awareness or care.

    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
     fashion
    -0.07
     ligne
    -0.07
    	email
    -0.07
     podium
    -0.06
     smugg
    -0.06
    .bz
    -0.06
    .gif
    -0.06
    udd
    -0.06
    =read
    -0.06
     UIP
    -0.06
    POSITIVE LOGITS
    )는
    0.06
     BİL
    0.06
    _/
    0.06
    롤
    0.06
    .compress
    0.06
     Truman
    0.06
    인데
    0.06
    类
    0.06
    Decor
    0.06
     Norse
    0.06
    Activations Density 0.031%

    No Known Activations