Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 89988
    Prev
    Next
    INDEX
    Explanations

    medication

    np_max-act · gemini-2.0-flash

    The neuron detects clinical pharmacy and medication‐related terminology (e.g. “medication,” “pharmacist,” “pharmacy,” and “medication‐related”).

    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
     gust
    -0.06
     esp
    -0.06
     Leigh
    -0.06
    ้าก
    -0.06
    	call
    -0.06
     prayers
    -0.06
    encer
    -0.06
     věn
    -0.06
    .EN
    -0.06
    istro
    -0.06
    POSITIVE LOGITS
    .argv
    0.07
     chặt
    0.07
    715
    0.07
     seventh
    0.07
     tens
    0.07
     barang
    0.06
    .axis
    0.06
    (cols
    0.06
    Rotation
    0.06
     張
    0.06
    Activations Density 0.019%

    No Known Activations