© 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. 25647
    Prev
    Next
    INDEX
    Explanations

    classify

    np_max-act · gemini-2.0-flash

    The neuron fires on wording that describes dividing or classifying things into categories (e.g. “classified into two groups,” “divided into three types,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    methods related to soldering and assembly in electronics.

    oai_token-act-pair · gpt-4o-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
    11
    -0.07
     nationally
    -0.06
    ל
    -0.06
    .cert
    -0.06
     바로
    -0.06
    .skill
    -0.06
    NULL
    -0.06
     pne
    -0.06
    .tree
    -0.06
    اصر
    -0.06
    POSITIVE LOGITS
     темп
    0.07
     createUser
    0.07
     داو
    0.06
    osen
    0.06
    '),('
    0.06
    услов
    0.06
     Appalachian
    0.06
     audi
    0.06
    Editar
    0.06
     Ou
    0.06
    Activations Density 0.021%

    No Known Activations