© 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. 128742
    Prev
    Next
    INDEX
    Explanations

    markets

    np_max-act · gemini-2.0-flash

    This neuron never activates on any content—it does not detect or respond to 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
     constraints
    -0.07
    럭
    -0.07
     활용
    -0.07
     Tests
    -0.07
     rewards
    -0.06
     Fellow
    -0.06
     wisdom
    -0.06
     sciences
    -0.06
    ीच
    -0.06
    ının
    -0.06
    POSITIVE LOGITS
     ترب
    0.07
    roj
    0.07
     пищ
    0.07
     الجن
    0.06
    .existsSync
    0.06
     caut
    0.06
     dbHelper
    0.06
    ственных
    0.06
     shouting
    0.06
    ственной
    0.06
    Activations Density 0.000%

    No Known Activations