© 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. 893
    Prev
    Next
    INDEX
    Explanations

    code files

    np_max-act · gemini-2.0-flash

    This neuron responds to parts of Drupal theme template file names, especially the “page--… .tpl.php” pattern.

    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
    alley
    -0.07
     Росії
    -0.06
    OOSE
    -0.06
    riteria
    -0.06
    zyć
    -0.06
    IllegalAccessException
    -0.06
     }}>
    -0.06
    823
    -0.06
     acting
    -0.06
    文献
    -0.06
    POSITIVE LOGITS
     teased
    0.07
     mann
    0.07
     town
    0.06
     nikdo
    0.06
     standoff
    0.06
     dalších
    0.06
     heute
    0.06
     döndü
    0.06
     진짜
    0.06
     lanz
    0.06
    Activations Density 0.091%

    No Known Activations