© 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. 109411
    Prev
    Next
    INDEX
    Explanations

    business services

    np_max-act · gemini-2.0-flash

    The neuron responds to upbeat, self-promotional corporate language—words expressing pride, commitment, innovation, and delivering value.

    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
     patient
    -0.07
     gz
    -0.07
    -speaking
    -0.07
    lendirme
    -0.07
    .Patient
    -0.06
     Penis
    -0.06
    Hillary
    -0.06
    .Mock
    -0.06
    accine
    -0.06
     доктор
    -0.06
    POSITIVE LOGITS
     وح
    0.07
    藝
    0.07
    /posts
    0.06
     Prairie
    0.06
    'aff
    0.06
    นด
    0.06
     أغ
    0.06
    <iostream
    0.06
    Х
    0.06
    _link
    0.06
    Activations Density 0.115%

    No Known Activations