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. 15-RESID-POST-AA
    6. 11492
    Prev
    Next
    INDEX
    Explanations

    negative prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eres
    -0.06
     Really
    -0.06
     retrieve
    -0.06
    aviour
    -0.06
    viso
    -0.06
    enzhen
    -0.06
    kir
    -0.06
    刻
    -0.06
    -football
    -0.06
     criterion
    -0.06
    POSITIVE LOGITS
    xoops
    0.07
    _touch
    0.06
     olmadı
    0.06
     виб
    0.06
    [
    0.06
    +"<
    0.06
    ChangeEvent
    0.06
     arom
    0.06
      				
    0.06
    ","","
    0.06
    Activations Density 0.010%

    No Known Activations