© 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. 91079
    Prev
    Next
    INDEX
    Explanations

    video

    np_max-act · gemini-2.0-flash

    financial distress associated with oil and gas firms.

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

    This neuron responds to mentions of sourcing or supporting local designers and related community-oriented business terms.

    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
    Routine
    -0.07
    写
    -0.06
     extra
    -0.06
    َف
    -0.06
     Markup
    -0.06
    Clin
    -0.06
    Creator
    -0.06
    Extent
    -0.06
    Portal
    -0.06
    Spec
    -0.06
    POSITIVE LOGITS
    _LANGUAGE
    0.07
    ******/↵
    0.07
    ustralian
    0.06
     MatButtonModule
    0.06
     specular
    0.06
    ращи
    0.06
     tòa
    0.06
    ((__
    0.06
    LIBINT
    0.06
    atchewan
    0.06
    Activations Density 0.367%

    No Known Activations