© 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. 13069
    Prev
    Next
    INDEX
    Explanations

    much

    np_max-act · gemini-2.0-flash

    The neuron detects expressions of gratitude (e.g. “thank you,” “thanks so much,” etc.).

    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
    찌
    -0.07
    .Lines
    -0.06
    "}}↵
    -0.06
    Alarm
    -0.06
     �
    -0.06
     چرخ
    -0.06
    Rooms
    -0.06
    [g
    -0.06
    aims
    -0.06
     Surveillance
    -0.06
    POSITIVE LOGITS
     دين
    0.07
    Basically
    0.07
    _kernel
    0.06
     Stark
    0.06
    -name
    0.06
     jLabel
    0.06
    @section
    0.06
    _Callback
    0.06
     duas
    0.06
    ボ
    0.06
    Activations Density 0.024%

    No Known Activations