© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 7953
    Prev
    Next
    INDEX
    Explanations

    "for the most part"

    np_max-act · gemini-2.0-flash

    This neuron responds to words and phrases that express partial extent or qualification (e.g., “part,” “extent,” “particular,” “for the most part”).

    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
     Merkezi
    -0.07
    another
    -0.06
    ,让
    -0.06
     Another
    -0.06
    Ch
    -0.06
     fulfilled
    -0.06
    left
    -0.06
    Partition
    -0.06
    K
    -0.06
    android
    -0.06
    POSITIVE LOGITS
    限定
    0.07
     Corpus
    0.06
     oversee
    0.06
    λέον
    0.06
    ΙΣΤ
    0.06
    (([
    0.06
     MSE
    0.06
    .newaxis
    0.06
     ImVec
    0.06
     щодо
    0.06
    Activations Density 0.032%

    No Known Activations