© 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. 25340
    Prev
    Next
    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash

    The neuron detects “in the [NOUN]” phrases, especially in superlative or comparative contexts like “the most beautiful in the world” or “the smartest woman in the room.”

    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
    литель
    -0.07
     pořad
    -0.07
    Numeric
    -0.07
    Smoke
    -0.06
     перей
    -0.06
    ccb
    -0.06
    zim
    -0.06
     when
    -0.06
    ocop
    -0.06
    Zend
    -0.06
    POSITIVE LOGITS
     polo
    0.07
    geme
    0.07
     ワ
    0.06
    (matrix
    0.06
     Klan
    0.06
     surviv
    0.06
    traditional
    0.06
     mage
    0.06
    	ct
    0.06
    :",↵
    0.06
    Activations Density 0.012%

    No Known Activations