Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 13225
    Prev
    Next
    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash

    The neuron flags the first significant content word that starts a new section or paragraph—essentially marking section headings or paragraph-opening keywords.

    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
     improvis
    -0.07
    .postMessage
    -0.07
     DON
    -0.06
    APPLICATION
    -0.06
     Cham
    -0.06
     Gat
    -0.06
    -summary
    -0.06
     cryptocurrencies
    -0.06
    ]-
    -0.06
     Widow
    -0.06
    POSITIVE LOGITS
    ìm
    0.07
     automáticamente
    0.06
    .converter
    0.06
     Washing
    0.06
    iệt
    0.06
    :UIAlert
    0.06
    amar
    0.06
     rush
    0.06
    FieldType
    0.06
     FStar
    0.06
    Activations Density 0.019%

    No Known Activations