© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 12372
    Prev
    Next
    INDEX
    Explanations

    .com

    np_max-act · gemini-2.0-flash

    promotional content related to ticket sales for events and concerts.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron activates on numeric tokens and digit‐containing sequences (e.g. phone numbers and number‐based domain parts).

    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
    braco
    -0.06
    relu
    -0.06
    ترك
    -0.06
    ket
    -0.06
    (xpath
    -0.06
     recieved
    -0.06
    Ra
    -0.06
    resar
    -0.06
    _REFERER
    -0.06
    istance
    -0.06
    POSITIVE LOGITS
     *)__
    0.07
    HasKey
    0.06
    $product
    0.06
     OTHER
    0.06
    (!_
    0.06
    <UFunction
    0.06
     Hof
    0.06
    ][_
    0.06
     folk
    0.06
    종
    0.06
    Activations Density 0.010%

    No Known Activations