© 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. 89670
    Prev
    Next
    INDEX
    Explanations

    articles

    np_max-act · gemini-2.0-flash

    This neuron responds to the standalone indefinite article “A” when it begins a list item (e.g. “A star-themed jewelry box,” “A tarot deck,” etc.).

    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
    |
    -0.07
     staveb
    -0.07
     Friedman
    -0.07
    úc
    -0.07
    quisar
    -0.06
    _barrier
    -0.06
      
    -0.06
    ș
    -0.06
     Nie
    -0.06
    방법
    -0.06
    POSITIVE LOGITS
    .RequestBody
    0.07
     TO
    0.06
    ominator
    0.06
    !I
    0.06
     withString
    0.06
     To
    0.06
     You
    0.06
    _HAL
    0.06
    You
    0.06
    .You
    0.06
    Activations Density 0.069%

    No Known Activations