© 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. 89882
    Prev
    Next
    INDEX
    Explanations

    hand

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of hand‐craftsmanship, i.e. words indicating items are made or finished by hand.

    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
    087
    -0.07
    �
    -0.06
     مصرف
    -0.06
    сию
    -0.06
     Protocol
    -0.06
    τερο
    -0.06
     srand
    -0.06
    ولات
    -0.06
     Polo
    -0.06
    MEMORY
    -0.06
    POSITIVE LOGITS
    (Yii
    0.07
     kre
    0.07
     loài
    0.07
    VisualStyleBackColor
    0.07
    .“
    0.07
    _metric
    0.06
     opioids
    0.06
    枝
    0.06
     №
    0.06
     menggunakan
    0.06
    Activations Density 0.020%

    No Known Activations