© 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. 42707
    Prev
    Next
    INDEX
    Explanations

    historical events

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on the titles of government‐office incumbents (e.g. “Monarch,” “Prime Minister,” and related header words) in yearly event summary pages.

    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
    ])↵↵
    -0.07
    ubo
    -0.07
     clearance
    -0.07
     danced
    -0.06
     credentials
    -0.06
     ROAD
    -0.06
    ering
    -0.06
    _BUF
    -0.06
    建设
    -0.06
    _SELECTION
    -0.06
    POSITIVE LOGITS
    cripcion
    0.07
    spinner
    0.07
    /as
    0.07
    leur
    0.06
    dimension
    0.06
    (_:
    0.06
     موقع
    0.06
     squirt
    0.06
    ัญ
    0.06
    TER
    0.06
    Activations Density 0.006%

    No Known Activations