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. 128918
    Prev
    Next
    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    This neuron fires on instances of the word “to” used as part of code comments or instructions (e.g. in “used to …”).

    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
    GLISH
    -0.07
    ��
    -0.07
     PACKAGE
    -0.06
     sider
    -0.06
    wyn
    -0.06
    ふ
    -0.06
    入れ
    -0.06
     rupture
    -0.06
     Timothy
    -0.06
     compromises
    -0.06
    POSITIVE LOGITS
    LP
    0.07
    _ut
    0.07
     Death
    0.06
    .e
    0.06
     ali
    0.06
     líder
    0.06
    ável
    0.06
     HEAD
    0.06
     Aunt
    0.06
    луата
    0.06
    Activations Density 0.000%

    No Known Activations