© 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. 19-RESID-POST-AA
    6. 10985
    Prev
    Next
    INDEX
    Explanations

    :

    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
    stants
    -0.07
     средств
    -0.06
    وقيت
    -0.06
    ả
    -0.06
     newX
    -0.06
     explanations
    -0.06
    อลลาร
    -0.06
    subjects
    -0.06
    -tm
    -0.06
    iew
    -0.06
    POSITIVE LOGITS
     unlocking
    0.08
    =plt
    0.07
    usi
    0.07
     dood
    0.06
    maybe
    0.06
    income
    0.06
    izza
    0.06
    .dead
    0.06
     ROM
    0.06
    &R
    0.06
    Activations Density 0.045%

    No Known Activations