© 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. 13427
    Prev
    Next
    INDEX
    Explanations

    find command

    np_max-act · gemini-2.0-flash

    This neuron detects usages of the Unix “find” command (with its options like -type, -name, -exec, etc.) in shell scripts.

    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
    ceptor
    -0.07
    ереч
    -0.07
     های
    -0.07
    mek
    -0.06
    他們
    -0.06
    ilate
    -0.06
    eken
    -0.06
     pharmacies
    -0.06
     lien
    -0.06
    很多
    -0.06
    POSITIVE LOGITS
     Lack
    0.06
     spac
    0.06
    Venue
    0.06
    .timedelta
    0.06
    dbc
    0.06
    ($.
    0.06
     discrepan
    0.06
    /lgpl
    0.05
     Breitbart
    0.05
     Yoga
    0.05
    Activations Density 0.002%

    No Known Activations