© 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. 5912
    Prev
    Next
    INDEX
    Explanations

    login authentication

    np_max-act · gemini-2.0-flash

    The neuron activates on technical terms related to user authentication and login flows (e.g. “login,” “authentication,” “redirect,” “Facebook login page”).

    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
     코드
    -0.07
    ots
    -0.06
    оглас
    -0.06
    .attach
    -0.06
     CALC
    -0.06
    コード
    -0.06
    utschein
    -0.06
     använd
    -0.06
     rift
    -0.06
    ABCDE
    -0.06
    POSITIVE LOGITS
     سرمایه
    0.06
    _ped
    0.06
     implicit
    0.06
     전세
    0.06
     electron
    0.06
    more
    0.06
    values
    0.06
    社
    0.06
    _normal
    0.06
    mono
    0.06
    Activations Density 0.012%

    No Known Activations