© 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
    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. 68833
    Prev
    Next
    INDEX
    Explanations

    ?

    np_max-act · gemini-2.0-flash

    This neuron activates on the “Address:” field label in form‐style text.

    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
    Attach
    -0.07
    したら
    -0.07
    ấm
    -0.06
    vergence
    -0.06
     Evelyn
    -0.06
     Lot
    -0.06
     hamstring
    -0.06
    ота
    -0.06
     tantal
    -0.06
    elope
    -0.06
    POSITIVE LOGITS
    .Operation
    0.06
    Guest
    0.06
     relativ
    0.06
    /forms
    0.06
    _orders
    0.06
     dataSize
    0.06
     случа
    0.06
     العلم
    0.06
     resourceId
    0.06
     Norm
    0.06
    Activations Density 0.040%

    No Known Activations