© 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. 118533
    Prev
    Next
    INDEX
    Explanations

    graduation and school

    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
     briefed
    -0.07
    ryptography
    -0.07
    _;↵
    -0.06
    انس
    -0.06
     марш
    -0.06
     외
    -0.06
     plagiarism
    -0.06
    omat
    -0.06
    MainThread
    -0.06
    Mer
    -0.06
    POSITIVE LOGITS
    (expr
    0.08
     mệnh
    0.06
     tun
    0.06
    ffic
    0.06
    _atts
    0.06
     бит
    0.06
     Belmont
    0.06
     mohli
    0.06
    	nil
    0.06
    \Form
    0.06
    Activations Density 0.042%

    No Known Activations