© 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. 12411
    Prev
    Next
    INDEX
    Explanations

    zero

    np_max-act · gemini-2.0-flash

    This neuron never activates—it doesn’t detect any pattern in the input.

    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
    .ButterKnife
    -0.07
    ▋▋
    -0.07
    되었습니다
    -0.06
    醴醴
    -0.06
    -util
    -0.06
    SingleNode
    -0.06
    illez
    -0.06
     memes
    -0.06
    丁目
    -0.06
    Mbps
    -0.06
    POSITIVE LOGITS
    module
    0.07
    .EX
    0.06
    INCREMENT
    0.06
    $('.
    0.06
    Rotation
    0.06
    Cipher
    0.06
     Greater
    0.06
     checkBox
    0.06
    UY
    0.06
    publication
    0.06
    Activations Density 0.004%

    No Known Activations