Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 57384
    Prev
    Next
    INDEX
    Explanations

    -time

    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
     kvinn
    -0.07
    vil
    -0.06
     ccp
    -0.06
     STANDARD
    -0.06
     Sequential
    -0.06
    씀
    -0.06
     bella
    -0.06
    .Usuario
    -0.06
     گذاری
    -0.06
    roperties
    -0.06
    POSITIVE LOGITS
    snd
    0.08
    AGING
    0.07
     цій
    0.07
     регуляр
    0.07
     بـ
    0.07
     IOCTL
    0.06
     эти
    0.06
    таж
    0.06
    奇
    0.06
    -minute
    0.06
    Activations Density 0.001%

    No Known Activations