© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 90760
    Prev
    Next
    INDEX
    Explanations

    ational

    np_max-act · gemini-2.0-flash

    This neuron activates on words denoting domestic or caregiving duties (e.g., “bills,” “kids,” “day”).

    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
     Graz
    -0.07
     Gecko
    -0.07
    }$
    -0.07
     дод
    -0.06
     catast
    -0.06
     dhcp
    -0.06
     История
    -0.06
    津
    -0.06
    گر
    -0.06
     glory
    -0.06
    POSITIVE LOGITS
    _losses
    0.07
     prost
    0.06
    _CHARACTER
    0.06
    bitset
    0.06
     آسیاب
    0.06
    �
    0.06
    -ver
    0.06
    stantiate
    0.06
    .findElement
    0.06
     strcat
    0.06
    Activations Density 0.216%

    No Known Activations