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. 19-RESID-POST-AA
    6. 35428
    Prev
    Next
    INDEX
    Explanations

    code

    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
     Lastly
    -0.07
     труб
    -0.07
     orth
    -0.06
    nx
    -0.06
    =no
    -0.06
     tránh
    -0.06
     有
    -0.06
    dw
    -0.06
     Audio
    -0.06
     nodeName
    -0.06
    POSITIVE LOGITS
     ecs
    0.07
     Zam
    0.07
    ven
    0.07
    wk
    0.07
    册
    0.06
    composite
    0.06
    sessions
    0.06
    resentation
    0.06
    atables
    0.06
    려요
    0.06
    Activations Density 0.004%

    No Known Activations