© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 42733
    Prev
    Next
    INDEX
    Explanations

    IDs and numbers

    np_max-act · gemini-2.0-flash

    This neuron activates on parts of the text that represent placeholder name identifiers (the “NAME_” tokens and their following numeric IDs).

    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
     tilted
    -0.07
    Roles
    -0.07
     Mec
    -0.07
    تس
    -0.07
     disease
    -0.07
     Від
    -0.06
     stained
    -0.06
     augmentation
    -0.06
    主人
    -0.06
     Thompson
    -0.06
    POSITIVE LOGITS
     bylo
    0.06
    (pol
    0.06
    awah
    0.06
     обеспечива
    0.06
     Skywalker
    0.06
     STM
    0.06
    -->
    0.06
    odu
    0.06
     skulle
    0.06
    (pow
    0.06
    Activations Density 0.004%

    No Known Activations