© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 127172
    Prev
    Next
    INDEX
    Explanations

    Tilde symbol

    np_max-act · gemini-2.0-flash

    references and citations related to chemical substance data and properties.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron detects floating‐point numerical values (decimal measurements) in the text.

    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
    PB
    -0.07
    ).*
    -0.06
     necklace
    -0.06
    achts
    -0.06
    _npc
    -0.06
    sure
    -0.06
     ),↵↵
    -0.06
    vert
    -0.06
    BEST
    -0.06
    POSITIVE LOGITS
     unmistak
    0.06
    .msg
    0.06
    ельно
    0.06
     transparency
    0.06
    坐在
    0.06
     abandoning
    0.06
     INTERFACE
    0.06
    .Calendar
    0.06
     Islamic
    0.06
    .GL
    0.06
    Activations Density 0.000%

    No Known Activations