© 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. 109404
    Prev
    Next
    INDEX
    Explanations

    #

    np_max-act · gemini-2.0-flash

    This neuron detects the shell‐script comment marker (“#”) and elements of comment lines.

    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
     Flame
    -0.06
     coupons
    -0.06
     mailed
    -0.06
     birçok
    -0.06
     showc
    -0.06
     Вс
    -0.06
     Bring
    -0.06
     hled
    -0.05
    급
    -0.05
    chains
    -0.05
    POSITIVE LOGITS
     مل
    0.07
    (rows
    0.07
    .addRow
    0.07
    committed
    0.07
    FAQ
    0.06
    ...↵↵
    0.06
     реак
    0.06
    нивер
    0.06
     ■
    0.06
     FUNCTIONS
    0.06
    Activations Density 0.008%

    No Known Activations