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. 92922
    Prev
    Next
    INDEX
    Explanations

    ium

    np_max-act · gemini-2.0-flash

    The neuron is triggered by numeric tokens expressing fractional or decimal values (e.g. numbers with a decimal point).

    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
     exquisite
    -0.07
    mailer
    -0.06
     ourselves
    -0.06
    DownLatch
    -0.06
     �
    -0.06
    edd
    -0.06
    Storage
    -0.06
     metabolism
    -0.06
    -choice
    -0.05
    connection
    -0.05
    POSITIVE LOGITS
    韓
    0.07
    gx
    0.07
     стать
    0.07
     newPath
    0.06
     #"
    0.06
     ó
    0.06
    ―
    0.06
     уча
    0.06
     rozvoj
    0.06
     đứng
    0.06
    Activations Density 0.003%

    No Known Activations