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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 8498
    Prev
    Next
    INDEX
    Explanations

    sole

    np_max-act · gemini-2.0-flash

    This neuron activates on the word “sole” when it’s used to mark exclusive status (e.g. sole owner, sole shareholder, sole responsibility, sole provider).

    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
    Dynamic
    -0.07
    Your
    -0.07
    appear
    -0.06
     furthermore
    -0.06
    Pago
    -0.06
     обязательно
    -0.06
    Brown
    -0.06
    -but
    -0.06
    lero
    -0.06
    -supported
    -0.06
    POSITIVE LOGITS
    _modifier
    0.06
     Pendant
    0.06
     Poke
    0.06
    _RULE
    0.06
    -е
    0.06
    062
    0.06
    ограф
    0.06
    ROL
    0.06
     всех
    0.06
     вспом
    0.06
    Activations Density 0.009%

    No Known Activations