© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 126150
    Prev
    Next
    INDEX
    Explanations

    productivity

    np_max-act · gemini-2.0-flash

    The neuron is triggered by occurrences of the word “productivity.”

    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
    _cluster
    -0.07
     geschichten
    -0.07
    573
    -0.07
     emergency
    -0.06
    -new
    -0.06
     sole
    -0.06
     september
    -0.06
     선거
    -0.06
     coward
    -0.06
    ября
    -0.06
    POSITIVE LOGITS
     productivity
    0.11
     productive
    0.09
    ड़क
    0.08
    agenda
    0.07
     BCM
    0.07
    profit
    0.07
    ritable
    0.07
    Quite
    0.07
     Pessoa
    0.07
    นด
    0.07
    Activations Density 0.007%

    No Known Activations