© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 118096
    Prev
    Next
    INDEX
    Explanations

    Contractions and "Mr"

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Customer
    -0.08
     dần
    -0.07
     customer
    -0.07
    Children
    -0.07
    Cisco
    -0.07
     kalk
    -0.07
    �
    -0.06
    telegram
    -0.06
     caracter
    -0.06
     الس
    -0.06
    POSITIVE LOGITS
    :str
    0.07
     "'");↵
    0.06
     invert
    0.06
     підвищ
    0.06
     bacheca
    0.06
     갤로그
    0.06
     iNdEx
    0.06
    InMillis
    0.06
     знач
    0.06
    .Minute
    0.06
    Activations Density 0.047%

    No Known Activations