© 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. 125048
    Prev
    Next
    INDEX
    Explanations

    ulate

    np_max-act · gemini-2.0-flash

    This neuron responds to mentions of particulate matter (e.g., “PM,” “particulate,” “matter,” “PM10”) in discussions of air pollution.

    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
    FromNib
    -0.06
     reputation
    -0.06
    _vert
    -0.06
     setObject
    -0.06
     Odyssey
    -0.06
     invokingState
    -0.06
    策
    -0.06
    colors
    -0.06
    竟
    -0.06
    _ER
    -0.06
    POSITIVE LOGITS
    .
    0.07
    anticipated
    0.07
    _RM
    0.07
     reciprocal
    0.07
    abelle
    0.06
     affirmative
    0.06
    ุดท
    0.06
     взя
    0.06
     SEM
    0.06
    United
    0.06
    Activations Density 0.003%

    No Known Activations