© 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. 30136
    Prev
    Next
    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash

    The neuron is looking for non‐alphanumeric characters (i.e. punctuation and symbols) in the text.

    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
    HostName
    -0.06
     Dodgers
    -0.06
     Heads
    -0.06
    enco
    -0.06
    urahan
    -0.06
     franc
    -0.06
    Υ
    -0.06
    <hr
    -0.06
    ustainable
    -0.06
     Ω
    -0.06
    POSITIVE LOGITS
     lado
    0.07
    lerimiz
    0.07
     süt
    0.06
    tutorial
    0.06
     Span
    0.06
    .setFill
    0.06
     JOptionPane
    0.06
     IDEOGRAPH
    0.06
     fetched
    0.06
     пров
    0.06
    Activations Density 0.014%

    No Known Activations