© 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. 63216
    Prev
    Next
    INDEX
    Explanations

    desires or requests

    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
    队
    -0.07
     soutě
    -0.07
     Clay
    -0.06
    Toggle
    -0.06
     Enum
    -0.06
    Issuer
    -0.06
    .Alert
    -0.06
    。あ
    -0.06
     či
    -0.06
     TOKEN
    -0.06
    POSITIVE LOGITS
    باح
    0.07
    aniem
    0.07
    .FieldName
    0.06
    ,,
    0.06
     millions
    0.06
    Buf
    0.06
    electron
    0.06
    ##↵
    0.06
     *</
    0.06
    HZ
    0.06
    Activations Density 0.022%

    No Known Activations