© 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. 92469
    Prev
    Next
    INDEX
    Explanations

    phrase

    np_max-act · gemini-2.0-flash

    This neuron spotlights user requests to “rephrase” or similarly ask for something to be re­phrased.

    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
     contact
    -0.06
    -black
    -0.06
     webpage
    -0.06
     poorer
    -0.06
    ิกายน
    -0.06
     Cookbook
    -0.06
    Dragon
    -0.06
     досвід
    -0.05
    .bus
    -0.05
    надлеж
    -0.05
    POSITIVE LOGITS
     fichier
    0.07
     xin
    0.07
    Aligned
    0.07
    ines
    0.06
    (collection
    0.06
     Kim
    0.06
     brightness
    0.06
    .getWidth
    0.06
    UMB
    0.06
    Fragment
    0.06
    Activations Density 0.011%

    No Known Activations