© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 12572
    Prev
    Next
    INDEX
    Explanations

    Blush

    np_max-act · gemini-2.0-flash

    characters involved in romantic and intimate scenarios.

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

    This neuron never activates—it doesn’t detect any features.

    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
     zru
    -0.08
     API
    -0.06
    拍
    -0.06
    ソン
    -0.06
    Ports
    -0.06
     kéo
    -0.06
    _format
    -0.06
    '*
    -0.06
     Liter
    -0.06
    .isOpen
    -0.06
    POSITIVE LOGITS
     embarrassed
    0.07
     adjust
    0.07
     planted
    0.07
    ivism
    0.07
     adapt
    0.07
     responder
    0.06
    boss
    0.06
     Understand
    0.06
     glowing
    0.06
     backstage
    0.06
    Activations Density 0.004%

    No Known Activations