© 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. 41649
    Prev
    Next
    INDEX
    Explanations

    parentheses and curly braces

    np_max-act · gemini-2.0-flash

    This neuron activates on null literal checks in code (e.g., comparisons or assignments involving “null”).

    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
    Acceleration
    -0.08
    trasound
    -0.07
    .resize
    -0.07
     Có
    -0.06
    peri
    -0.06
     deprecated
    -0.06
     Australia
    -0.06
    Incomplete
    -0.06
     информации
    -0.06
    ANDING
    -0.06
    POSITIVE LOGITS
    KeyPress
    0.07
     Mitsubishi
    0.07
    หมาย
    0.07
    Dave
    0.06
    (fabs
    0.06
     shim
    0.06
    strlen
    0.06
    їв
    0.06
     ChatColor
    0.06
     selv
    0.06
    Activations Density 0.022%

    No Known Activations