© 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. 30577
    Prev
    Next
    INDEX
    Explanations

    stop words

    np_max-act · gemini-2.0-flash

    This neuron responds to topic-heading phrases that begin with “The … of …,” i.e., list-item titles starting with “The” followed by a noun (e.g. “The role of …,” “The impact of …”).

    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
     cof
    -0.07
     centuries
    -0.07
     queued
    -0.07
    泊
    -0.06
    pegawai
    -0.06
     adviser
    -0.06
     queue
    -0.06
    Request
    -0.06
     Gaut
    -0.06
    valid
    -0.06
    POSITIVE LOGITS
     cancelButtonTitle
    0.06
    (prog
    0.06
     purch
    0.06
    ("-
    0.06
    _pickle
    0.06
    (jPanel
    0.06
    Information
    0.06
    _predictions
    0.06
    /windows
    0.06
    (names
    0.06
    Activations Density 0.030%

    No Known Activations