© 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. 41397
    Prev
    Next
    INDEX
    Explanations

    mal

    np_max-act · gemini-2.0-flash

    This neuron fires on words beginning with the prefix “mal-,” such as malnutrition, maladaptation, malformation, malabsorption, and malocclusion.

    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
    issa
    -0.07
    ix
    -0.07
    1
    -0.07
    .ejb
    -0.07
    AGIC
    -0.07
    ouse
    -0.07
     entityId
    -0.07
    џџџџџџџџ
    -0.07
     تور
    -0.07
     Starr
    -0.07
    POSITIVE LOGITS
     mal
    0.11
     Mal
    0.10
     Malcolm
    0.09
    mal
    0.08
    Mal
    0.08
    men
    0.08
    관리
    0.07
    MAL
    0.07
    -men
    0.07
     malfunction
    0.07
    Activations Density 0.011%

    No Known Activations