© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 110147
    Prev
    Next
    INDEX
    Explanations

    Network address families

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric literals (particularly floating‐point constants) in code.

    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
     touring
    -0.07
    (phase
    -0.06
     compact
    -0.06
    舌
    -0.06
     pale
    -0.06
     copy
    -0.06
    hait
    -0.06
     JK
    -0.06
     shading
    -0.05
     Зак
    -0.05
    POSITIVE LOGITS
    ingen
    0.08
    ;o
    0.07
    annya
    0.07
    ología
    0.06
    endpoint
    0.06
    mits
    0.06
     cancelButtonTitle
    0.06
     inclus
    0.06
    uggestions
    0.06
    'es
    0.06
    Activations Density 0.008%

    No Known Activations