© 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. 29625
    Prev
    Next
    INDEX
    Explanations

    al

    np_max-act · gemini-2.0-flash

    information related to ecological effects and biodiversity in aquatic environments.

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

    The neuron detects ecological habitat zone terms, especially references to “benthic” or “intertidal.”

    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
    fwrite
    -0.07
    ують
    -0.06
    progressbar
    -0.06
    لم
    -0.06
    ogle
    -0.06
     sagt
    -0.06
     vystav
    -0.06
    ют
    -0.06
    産
    -0.06
     CY
    -0.06
    POSITIVE LOGITS
     odds
    0.07
    (clicked
    0.06
    _PC
    0.06
    一区
    0.06
    aida
    0.06
    ูน
    0.06
    ์ก
    0.06
     έκ
    0.06
     cái
    0.06
    ikh
    0.06
    Activations Density 0.006%

    No Known Activations