© 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. 12799
    Prev
    Next
    INDEX
    Explanations

    /core

    np_max-act · gemini-2.0-flash

    The neuron is triggered by import statements bringing in core Angular symbols (e.g. “from '@angular/core’”).

    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
    Species
    -0.08
    GLIGENCE
    -0.06
    력을
    -0.06
     matchups
    -0.06
    ·
    -0.06
     gums
    -0.06
    bart
    -0.06
     certains
    -0.06
     respect
    -0.06
     dataSet
    -0.06
    POSITIVE LOGITS
    τιο
    0.07
    /core
    0.07
     AO
    0.06
    .IP
    0.06
    /angular
    0.06
    (KEY
    0.06
    aceutical
    0.06
    inicio
    0.06
     Ohio
    0.06
    :[↵
    0.06
    Activations Density 0.000%

    No Known Activations