© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 12244
    Prev
    Next
    INDEX
    Explanations

    aware

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of the word “aware” (especially in the phrase “aware of”).

    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
     Throne
    -0.08
     Filip
    -0.08
     チ
    -0.08
    .Template
    -0.07
     erhalten
    -0.07
     půj
    -0.07
     finish
    -0.07
    udit
    -0.07
     Song
    -0.07
     plunder
    -0.07
    POSITIVE LOGITS
     aware
    0.15
     Aware
    0.11
     awareness
    0.11
     unaware
    0.11
     Awareness
    0.10
    aware
    0.10
    -aware
    0.09
     beware
    0.07
    Ware
    0.07
    WARE
    0.07
    Activations Density 0.014%

    No Known Activations