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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 84801
    Prev
    Next
    INDEX
    Explanations

    biographies

    np_max-act · gemini-2.0-flash

    This neuron detects parenthetical profession or role labels (e.g. job titles) that follow people’s names.

    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
    aramel
    -0.07
     subsystem
    -0.07
     Wit
    -0.07
    increase
    -0.07
    acellular
    -0.07
    reverse
    -0.06
     anniversary
    -0.06
    worthy
    -0.06
     snowy
    -0.06
     depart
    -0.06
    POSITIVE LOGITS
     ¶
    0.07
    aso
    0.07
     quali
    0.06
     нього
    0.06
    \Client
    0.06
    �
    0.06
    setName
    0.06
     pornôs
    0.06
    claims
    0.06
     aras
    0.06
    Activations Density 0.024%

    No Known Activations