© 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. 127004
    Prev
    Next
    INDEX
    Explanations

    taught

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of having been taught or instructed (e.g. “I was taught,” “I learned”).

    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
     เจ
    -0.07
     이루
    -0.07
     wxString
    -0.07
    \Array
    -0.07
     下
    -0.07
    .fileName
    -0.06
     �
    -0.06
    umblr
    -0.06
    ери
    -0.06
    dragon
    -0.06
    POSITIVE LOGITS
     elev
    0.07
     detriment
    0.06
     Primary
    0.06
    Guess
    0.06
     ominous
    0.06
     Gold
    0.06
     primary
    0.06
    /class
    0.06
    -solid
    0.06
     maintains
    0.06
    Activations Density 0.023%

    No Known Activations