© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 5934
    Prev
    Next
    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash

    This neuron detects the presence of quotation‐mark tokens (i.e. double‐quote characters).

    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
    "Our
    -0.06
    _ENT
    -0.06
    .JSONArray
    -0.06
     Robot
    -0.06
    collision
    -0.06
    GBT
    -0.06
     jsonData
    -0.06
    -my
    -0.06
    Trigger
    -0.06
    Identification
    -0.06
    POSITIVE LOGITS
    asta
    0.07
    .be
    0.06
    лося
    0.06
    enis
    0.06
    -avatar
    0.06
     comprise
    0.06
    ív
    0.06
     têm
    0.06
     WX
    0.06
    �
    0.06
    Activations Density 0.030%

    No Known Activations