© 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. 109368
    Prev
    Next
    INDEX
    Explanations

    code syntax

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of the “contesto” (context) or related context-boundary phrases in Italian instruction text.

    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
     Provides
    -0.07
     Leslie
    -0.07
    																	
    -0.07
     myocard
    -0.07
    .JTable
    -0.06
    ocytes
    -0.06
    berg
    -0.06
     drove
    -0.06
    _node
    -0.06
     Manage
    -0.06
    POSITIVE LOGITS
    .ResponseWriter
    0.07
    _personal
    0.06
     unreachable
    0.06
    registers
    0.06
     supernatural
    0.06
     tranny
    0.06
     카지노
    0.06
    슬
    0.06
     stereotype
    0.06
    .utc
    0.06
    Activations Density 0.029%

    No Known Activations