© 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. 11-RESID-POST-AA
    11. 89868
    Prev
    Next
    INDEX
    Explanations

    email

    np_max-act · gemini-2.0-flash

    steps and instructions related to password management and account recovery.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron fires on mentions of email-based reset instructions—especially words like “email,” “link,” and related terms in a password-reset flow.

    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
     '$
    -0.08
     selecion
    -0.07
     Sab
    -0.06
    랜
    -0.06
     соп
    -0.06
     katı
    -0.06
     zdarma
    -0.06
    uarios
    -0.06
     Harold
    -0.05
     kino
    -0.05
    POSITIVE LOGITS
     gỗ
    0.07
    *)↵↵
    0.07
    "]);
↵
    0.07
    .fix
    0.07
     innovative
    0.07
    yclic
    0.07
    ++){
↵
    0.07
    /android
    0.07
    нув
    0.06
    `)↵
    0.06
    Activations Density 0.007%

    No Known Activations