© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 59325
    Prev
    Next
    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash

    The neuron detects instances of the phrase “build on” or “build upon,” marking where text refers to extending or continuing previous work.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     staring
    -0.08
    _trap
    -0.07
     hosts
    -0.07
     FAST
    -0.06
     appearance
    -0.06
     murders
    -0.06
     Rage
    -0.06
     heroes
    -0.06
    _RST
    -0.06
     axe
    -0.06
    POSITIVE LOGITS
     EntryPoint
    0.07
    不断
    0.07
    .MenuStrip
    0.07
     improves
    0.07
     Victor
    0.07
     выращи
    0.07
     �
    0.07
     경기도
    0.06
     قول
    0.06
    зано
    0.06
    Activations Density 0.010%

    No Known Activations