© 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. 55569
    Prev
    Next
    INDEX
    Explanations

    regards/incerely

    np_max-act · gemini-2.0-flash

    The neuron detects formal email sign-off phrases (valedictions) such as “Best regards.”

    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
     باشند
    -0.07
    sprite
    -0.07
    เช
    -0.06
    enville
    -0.06
     Sm
    -0.06
     folklore
    -0.06
    box
    -0.06
     прежде
    -0.05
     vítěz
    -0.05
    asy
    -0.05
    POSITIVE LOGITS
    eyJ
    0.07
     Resolve
    0.07
     automated
    0.07
    .func
    0.07
    ATAR
    0.07
    .published
    0.06
    UNIT
    0.06
    取得
    0.06
    ัจ
    0.06
     organizing
    0.06
    Activations Density 0.004%

    No Known Activations