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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 58645
    Prev
    Next
    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash

    The neuron responds to frequent function words—especially the conjunction “and” and the article “the.”

    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
    dropdown
    -0.06
    .Department
    -0.06
    .scrollHeight
    -0.06
    thin
    -0.06
    getStore
    -0.06
     clones
    -0.06
     repeatedly
    -0.06
     Costume
    -0.06
    _wo
    -0.05
    _endian
    -0.05
    POSITIVE LOGITS
     differed
    0.07
    inc
    0.07
     Spencer
    0.07
     offered
    0.07
     offer
    0.07
     moto
    0.07
    ano
    0.07
     contro
    0.06
    oa
    0.06
    ่างก
    0.06
    Activations Density 0.052%

    No Known Activations