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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 115297
    Prev
    Next
    INDEX
    Explanations

    Code/usernames/passwords

    np_max-act · gemini-2.0-flash

    This neuron detects text about user authentication and login functionality—discussion or code concerning credential checking, authentication flows, and session/login handling.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tooltips
    -0.07
     XC
    -0.07
    _signals
    -0.07
    ์พ
    -0.07
    ulations
    -0.06
    blocked
    -0.06
     revealing
    -0.06
    _categories
    -0.06
    rg
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    0.06
    imiter
    0.06
    ,//
    0.06
    ầ
    0.06
     homeland
    0.06
    ,System
    0.06
     bee
    0.06
    (helper
    0.06
    lluminate
    0.06
    ,pos
    0.06
    Activations Density 0.293%

    No Known Activations