© 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 (Instruct)
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 31887
    Prev
    Next
    INDEX
    Explanations

    experimenting

    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
     geek
    -0.07
    정부
    -0.06
     doctoral
    -0.06
    ASTER
    -0.06
    Angular
    -0.06
     leur
    -0.06
    oldur
    -0.06
     bolts
    -0.06
    geme
    -0.06
     czę
    -0.06
    POSITIVE LOGITS
    ăn
    0.06
     flakes
    0.06
    :SetText
    0.06
    =YES
    0.06
    (handle
    0.06
    ái
    0.06
     typography
    0.06
     investigates
    0.06
    (constants
    0.06
    .pub
    0.06
    Activations Density 0.014%

    No Known Activations