Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 41755
    Prev
    Next
    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    The neuron fires on the word “referred” when it’s used in definitional phrases (e.g. “referred to as…”).

    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
     garden
    -0.07
     voltage
    -0.07
     GAM
    -0.06
     빌
    -0.06
    警
    -0.06
    282
    -0.06
     Garden
    -0.06
     yarn
    -0.06
    、大
    -0.06
     Halloween
    -0.06
    POSITIVE LOGITS
    _UTF
    0.07
    _tF
    0.07
    PreferredGap
    0.07
    ishi
    0.06
     вв
    0.06
    ifs
    0.06
    OF
    0.06
    ee
    0.06
    irim
    0.06
     redu
    0.06
    Activations Density 0.006%

    No Known Activations