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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 99553
    Prev
    Next
    INDEX
    Explanations

    error messages

    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
     Huntington
    -0.07
     projection
    -0.07
    _stand
    -0.07
     νέ
    -0.07
    deps
    -0.07
     consequences
    -0.07
    /customer
    -0.06
     believes
    -0.06
    Doctor
    -0.06
    으나
    -0.06
    POSITIVE LOGITS
     期
    0.07
    _PERIOD
    0.06
     ADMIN
    0.06
    (job
    0.06
     wakeup
    0.06
     Diesel
    0.06
    只
    0.06
     tropical
    0.06
     Giang
    0.06
     Moines
    0.06
    Activations Density 0.013%

    No Known Activations