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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 58397
    Prev
    Next
    INDEX
    Explanations

    This neuron activates on words that occur at the very start of sentences or text chunks.

    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
    fte
    -0.07
    末
    -0.07
     Kunden
    -0.07
    ajo
    -0.06
    ją
    -0.06
    ários
    -0.06
     kann
    -0.06
     Procedures
    -0.06
    クロ
    -0.06
    xiety
    -0.06
    POSITIVE LOGITS
    "She
    0.07
    338
    0.06
     Cur
    0.06
     Glad
    0.06
    PasswordField
    0.06
    youtube
    0.06
     pursue
    0.06
    IFORM
    0.06
    quotes
    0.06
     renderItem
    0.06
    Activations Density 0.051%

    No Known Activations