© 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. 12991
    Prev
    Next
    INDEX
    Explanations

    code and documentation

    np_max-act · gemini-2.0-flash

    The neuron is keyed to spotting numeric constants—especially floating‐point literals—in code.

    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
     Rihanna
    -0.07
     公
    -0.07
     NJ
    -0.07
    tryside
    -0.07
          
    -0.07
    mamız
    -0.06
    xBC
    -0.06
     Cycling
    -0.06
    _TH
    -0.06
    ERGY
    -0.06
    POSITIVE LOGITS
     commands
    0.06
    _song
    0.06
     contestants
    0.06
    office
    0.06
     возможности
    0.06
     prod
    0.06
    _register
    0.06
     active
    0.06
    ทำงาน
    0.05
     camps
    0.05
    Activations Density 0.076%

    No Known Activations