© 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. 89859
    Prev
    Next
    INDEX
    Explanations

    punctuation and "other"

    np_max-act · gemini-2.0-flash

    This neuron detects the structured alphanumeric section and subsection labels (letter–number codes with hyphens, slashes, and semicolons) that mark patent or technical classification headings.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    technical specifications and classifications of products.

    oai_token-act-pair · gpt-4o-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
    纳
    -0.07
    ít
    -0.07
    (part
    -0.07
    _member
    -0.07
    elier
    -0.07
    レン
    -0.06
    旗
    -0.06
    OUN
    -0.06
    apping
    -0.06
    imately
    -0.06
    POSITIVE LOGITS
     Sole
    0.06
    .MiddleCenter
    0.06
     quali
    0.06
    ινή
    0.06
    م
    0.06
     č
    0.06
     formul
    0.06
     OSI
    0.06
     italiani
    0.06
     دنی
    0.06
    Activations Density 0.012%

    No Known Activations