© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 72933
    Prev
    Next
    INDEX
    Explanations

    Marketing/Business

    np_max-act · gemini-2.0-flash

    text related to service-oriented communication in business contexts.

    oai_token-act-pair · gpt-4o-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
    linewidth
    -0.07
    zer
    -0.06
    der
    -0.06
    Dragon
    -0.06
     Lin
    -0.06
    ωδ
    -0.06
    ski
    -0.06
    кін
    -0.06
    гор
    -0.06
     ORM
    -0.06
    POSITIVE LOGITS
     �
    0.06
     coordinate
    0.06
     attire
    0.06
    _install
    0.06
    按钮
    0.06
     UserController
    0.06
    _optimizer
    0.06
    (diff
    0.06
     أع
    0.06
    战斗
    0.06
    Activations Density 0.044%

    No Known Activations