© 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. 6430
    Prev
    Next
    INDEX
    Explanations

    Dates and ages

    np_max-act · gemini-2.0-flash

    The neuron specifically detects the patient’s age expressed in years inside parentheses.

    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
     kunnen
    -0.07
     Aunt
    -0.07
     Ash
    -0.06
     Gratuit
    -0.06
     roast
    -0.06
     Elf
    -0.06
     Sat
    -0.06
     fuel
    -0.06
     acknowled
    -0.06
     circular
    -0.06
    POSITIVE LOGITS
    migration
    0.07
                                                                                           
    0.07
                                                                                                   
    0.07
    """
    ↵
    ↵
    0.07
    _SRC
    0.07
     jerseys
    0.06
    188
    0.06
    (forms
    0.06
     â
    0.06
    licensed
    0.06
    Activations Density 0.001%

    No Known Activations