© 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
    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. 89137
    Prev
    Next
    INDEX
    Explanations

    IUCN Red List Species

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of IUCN Red List conservation status (e.g. “IUCN,” status assessments, and category labels like “LC”).

    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
     adequate
    -0.06
     satellite
    -0.06
     Betty
    -0.06
     histogram
    -0.06
     cohort
    -0.06
    Healthy
    -0.06
     stamina
    -0.06
    classmethod
    -0.06
     Frankie
    -0.06
     payroll
    -0.06
    POSITIVE LOGITS
    .collections
    0.07
    运
    0.07
     toReturn
    0.07
     envy
    0.06
     Aç
    0.06
     lia
    0.06
    雑
    0.06
    456
    0.06
     количество
    0.06
     PAGE
    0.06
    Activations Density 0.001%

    No Known Activations