© 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
    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. 58746
    Prev
    Next
    INDEX
    Explanations

    -header

    np_max-act · gemini-2.0-flash

    The neuron is detecting the presence of Bootstrap “modal” structure elements, e.g. tags with classes like modal-header, modal-dialog, modal-content, modal-body, or modal-footer.

    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
    (lib
    -0.06
    литель
    -0.06
    .AddRange
    -0.06
    โก
    -0.06
    coins
    -0.06
     magnet
    -0.06
    志
    -0.06
    ос
    -0.06
    νά
    -0.06
     nhỏ
    -0.06
    POSITIVE LOGITS
    '))↵↵↵
    0.07
     preamble
    0.07
    roe
    0.06
    CCI
    0.06
    Studies
    0.06
    ])
↵
↵
    0.06
     Україні
    0.06
     البلد
    0.06
     Monroe
    0.06
     OST
    0.06
    Activations Density 0.002%

    No Known Activations