© 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. 6965
    Prev
    Next
    INDEX
    Explanations

    Templates

    np_max-act · gemini-2.0-flash

    This neuron detects placeholder slots in template text, i.e. bracketed fields where user-specific information should be filled in.

    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
     goo
    -0.07
     А
    -0.07
    _trade
    -0.06
    红
    -0.06
    'LBL
    -0.06
     HCI
    -0.06
     Nh
    -0.06
     HID
    -0.06
     kunt
    -0.06
    อว
    -0.05
    POSITIVE LOGITS
    -delete
    0.07
    �
    0.07
    uffman
    0.07
     Query
    0.07
     Opp
    0.06
     виконання
    0.06
     commercial
    0.06
    odie
    0.06
     获取
    0.06
     inaugural
    0.06
    Activations Density 0.024%

    No Known Activations