© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 92190
    Prev
    Next
    INDEX
    Explanations

    Conditional statements/comparisons

    np_max-act · gemini-2.0-flash

    This neuron primarily fires on conditional “if” clauses—marking the start of hypothetical or conditional subordinate statements.

    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
     ви
    -0.07
     premi
    -0.06
    ']];↵
    -0.06
     INV
    -0.06
     인정
    -0.06
     happier
    -0.06
    �
    -0.06
    инку
    -0.06
     registrado
    -0.06
     diligent
    -0.06
    POSITIVE LOGITS
    ula
    0.07
     Wien
    0.06
     getItem
    0.06
    .issue
    0.06
    exit
    0.06
    preh
    0.06
    arters
    0.06
    Yii
    0.06
    ै।↵↵
    0.06
    -pre
    0.06
    Activations Density 0.099%

    No Known Activations