© 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
    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. 124960
    Prev
    Next
    INDEX
    Explanations

    >

    np_max-act · gemini-2.0-flash

    studies related to the examination of specific medical conditions or biological phenomena.

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

    The neuron doesn’t actually respond to any of the terms in these scientific abstracts—it remains inactive throughout.

    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
     Disabled
    -0.07
     OCR
    -0.07
     цьому
    -0.07
    éfono
    -0.06
    etleri
    -0.06
     게시
    -0.06
    rezent
    -0.06
    ีโ
    -0.06
    díl
    -0.06
    ,False
    -0.06
    POSITIVE LOGITS
    ै।
    0.06
    classed
    0.06
    carry
    0.06
    href
    0.06
    outed
    0.06
    (port
    0.06
    ctal
    0.06
     penalties
    0.06
    fet
    0.06
    istency
    0.06
    Activations Density 0.001%

    No Known Activations