© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 30156
    Prev
    Next
    INDEX
    Explanations

    't

    np_max-act · gemini-2.0-flash

    The neuron detects evaluative terms in sports scouting or performance commentary, flagging words that describe an athlete’s physical traits, skills, and tendencies.

    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
     interceptor
    -0.06
    .Store
    -0.06
     initWithNibName
    -0.06
     Verg
    -0.06
    _campaign
    -0.06
     projet
    -0.06
    :get
    -0.06
    OrderBy
    -0.06
    结构
    -0.06
    ヘ
    -0.06
    POSITIVE LOGITS
     Remark
    0.08
    ापन
    0.07
    國際
    0.07
     separately
    0.06
     blossom
    0.06
     празд
    0.06
    haus
    0.06
     caveat
    0.06
     čím
    0.06
    �택
    0.06
    Activations Density 0.020%

    No Known Activations