© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 128888
    Prev
    Next
    INDEX
    Explanations

    quiet

    np_max-act · gemini-2.0-flash

    This neuron responds to derived action‐words—especially verbs formed with Latin-style suffixes like –ate or –ize.

    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
    lose
    -0.07
    Tracks
    -0.07
    DRV
    -0.07
     Pour
    -0.06
    ,s
    -0.06
    cope
    -0.06
    $/,↵
    -0.06
    Pour
    -0.06
    _suffix
    -0.06
    /framework
    -0.06
    POSITIVE LOGITS
     QLabel
    0.07
    .propTypes
    0.07
    INSERT
    0.06
    iect
    0.06
    �
    0.06
     //!↵
    0.06
    ıc
    0.06
    还
    0.06
    .setRequest
    0.06
    干
    0.06
    Activations Density 0.279%

    No Known Activations