© 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. 60651
    Prev
    Next
    INDEX
    Explanations

    /

    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
    رانی
    -0.06
    rstrip
    -0.06
    vi
    -0.06
     CLL
    -0.06
     backlash
    -0.06
    -c
    -0.06
     confessed
    -0.06
    VI
    -0.06
    .documents
    -0.06
     ve
    -0.06
    POSITIVE LOGITS
    feas
    0.07
    ulpt
    0.07
     -↵↵
    0.07
     xương
    0.07
     \|
    0.06
     asla
    0.06
    (question
    0.06
     pollutants
    0.06
    tos
    0.06
     software
    0.06
    Activations Density 0.000%

    No Known Activations