© 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. 57793
    Prev
    Next
    INDEX
    Explanations

    *

    np_max-act · gemini-2.0-flash

    This neuron activates on the leading asterisk markers used in multi‐line block comments (e.g. the “*” at the start of each line in /** … */ docs).

    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
    Cr
    -0.06
    andre
    -0.06
     Sunday
    -0.06
    /.
    -0.06
     validate
    -0.06
    .onDestroy
    -0.06
     نوع
    -0.06
    .Usuario
    -0.06
    Boston
    -0.06
     Usage
    -0.06
    POSITIVE LOGITS
     Psych
    0.07
     reconstruct
    0.07
     harsh
    0.07
     защит
    0.07
     Discipline
    0.07
     dove
    0.06
    Eth
    0.06
     lieu
    0.06
     완
    0.06
    ギ
    0.06
    Activations Density 0.001%

    No Known Activations