© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 59427
    Prev
    Next
    INDEX
    Explanations

    animals and conservation

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of animal species names (e.g. “bison,” “peregrine,” “pronghorn,” “penguins,” etc.).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     Native
    -0.06
     Hava
    -0.06
     Bashar
    -0.06
    ої
    -0.06
     Quý
    -0.06
    爸
    -0.06
     Frames
    -0.06
     Gutenberg
    -0.06
    لمان
    -0.06
    Native
    -0.06
    POSITIVE LOGITS
     ček
    0.07
     nomin
    0.07
    (utf
    0.07
    	style
    0.07
    '",↵
    0.07
    jwt
    0.07
     CRE
    0.06
    /css
    0.06
    'user
    0.06
    buah
    0.06
    Activations Density 0.011%

    No Known Activations