© 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. 91087
    Prev
    Next
    INDEX
    Explanations

    may

    np_max-act · gemini-2.0-flash

    technical terms related to programming and software development.

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

    This neuron activates on second-person instructional language—words like “you,” “your,” “may,” “want,” and “make sure” in comments or docs giving the reader directions.

    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
     شوند
    -0.06
     onions
    -0.06
     ز
    -0.06
    ันยายน
    -0.06
    alar
    -0.05
     угод
    -0.05
    scaling
    -0.05
     cố
    -0.05
    ?>↵
    -0.05
     دهد
    -0.05
    POSITIVE LOGITS
     frameworks
    0.07
     richness
    0.07
    Shapes
    0.07
    $key
    0.07
    EO
    0.07
     NGX
    0.07
     setIs
    0.07
    .black
    0.06
    keleton
    0.06
     Ör
    0.06
    Activations Density 0.034%

    No Known Activations