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. 83412
    Prev
    Next
    INDEX
    Explanations

    head

    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
    ust
    -0.06
     Manor
    -0.06
     owes
    -0.06
     James
    -0.06
    Ip
    -0.06
     Surface
    -0.06
    sm
    -0.06
    400
    -0.06
    Harness
    -0.06
     british
    -0.06
    POSITIVE LOGITS
     pracov
    0.07
    ANGLES
    0.07
    .setViewport
    0.07
     підтрим
    0.07
    sonian
    0.06
     cardboard
    0.06
    _registered
    0.06
     ******************************************************************************/↵
    0.06
     essentials
    0.06
     зрения
    0.06
    Activations Density 0.017%

    No Known Activations