© 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
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 29909
    Prev
    Next
    INDEX
    Explanations

    children

    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
    ربع
    -0.06
     migrant
    -0.06
    _widgets
    -0.06
     bunun
    -0.06
    양
    -0.06
     exceedingly
    -0.06
    inema
    -0.06
    igrant
    -0.06
    一个
    -0.06
    Marks
    -0.06
    POSITIVE LOGITS
     Jes
    0.07
    ="_
    0.06
    umni
    0.06
    opper
    0.06
    DESC
    0.06
    /sp
    0.06
    .forEach
    0.06
     msgid
    0.06
    orse
    0.06
    testing
    0.06
    Activations Density 0.074%

    No Known Activations