© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 9196
    Prev
    Next
    INDEX
    Explanations

    't

    np_max-act · gemini-2.0-flash

    The neuron specializes in spotting numeric tokens—especially decimals and floating‐point numbers—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
    .Next
    -0.07
    21
    -0.06
     announcement
    -0.06
     ['.
    -0.06
    ميم
    -0.06
    ขว
    -0.06
    _when
    -0.06
    FontAwesomeIcon
    -0.06
    _totals
    -0.06
    -this
    -0.06
    POSITIVE LOGITS
    oriasis
    0.07
    _Master
    0.07
     Olympia
    0.06
    lys
    0.06
    дяки
    0.06
    (!_
    0.06
    Ơ
    0.06
    ій
    0.06
    ifer
    0.06
     рамках
    0.06
    Activations Density 0.140%

    No Known Activations