© 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. 92250
    Prev
    Next
    INDEX
    Explanations

    abilities/skills

    np_max-act · gemini-2.0-flash

    information about multiplayer online games.

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

    This neuron responds strongly to mentions of game‐related traits or mechanics—especially plural terms like “abilities,” “skills,” “strengths,” and “weaknesses.”

    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
     Penny
    -0.07
    ła
    -0.07
    currency
    -0.07
     disparity
    -0.06
     onChangeText
    -0.06
    -free
    -0.06
     Cellular
    -0.06
     연락
    -0.06
    rea
    -0.06
     params
    -0.06
    POSITIVE LOGITS
    CCCCCC
    0.07
     reconoc
    0.07
     Crimes
    0.06
     unknown
    0.06
     akan
    0.06
     unbearable
    0.06
     Combined
    0.06
     HIS
    0.06
    .General
    0.06
     pinterest
    0.06
    Activations Density 0.015%

    No Known Activations