© 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. 15-RESID-POST-AA
    6. 102091
    Prev
    Next
    INDEX
    Explanations

    a or an

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hoy
    -0.07
     Shr
    -0.07
     Kirby
    -0.06
     Kemp
    -0.06
    ें,
    -0.06
     Ub
    -0.06
     Deniz
    -0.06
     Ib
    -0.06
     Bol
    -0.06
     Pai
    -0.06
    POSITIVE LOGITS
     心
    0.07
    LEMENT
    0.06
    !');↵
    0.06
    ़क
    0.06
    第二
    0.06
    _TestCase
    0.06
    нут
    0.06
    ‌پدی
    0.06
    득
    0.06
    اما
    0.06
    Activations Density 0.053%

    No Known Activations