© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 12804
    Prev
    Next
    INDEX
    Explanations

    structured data

    np_max-act · gemini-2.0-flash

    This neuron activates on the prompt’s template labels and formatting tokens (e.g. “Restaurant name:”, “Description:”, “…”).

    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
    menin
    -0.07
    Card
    -0.07
     potato
    -0.07
     persuaded
    -0.06
     Cop
    -0.06
     supermarket
    -0.06
    .SharedPreferences
    -0.06
    ्ह
    -0.06
     thông
    -0.06
     alarm
    -0.06
    POSITIVE LOGITS
    .ex
    0.06
     gebruik
    0.06
    AtIndex
    0.06
    ,K
    0.06
    ：%
    0.06
    ρευ
    0.06
    ベ
    0.06
    	K
    0.06
    contains
    0.06
    prediction
    0.06
    Activations Density 0.006%

    No Known Activations