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. 9741
    Prev
    Next
    INDEX
    Explanations

    events and hosting

    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
    _plane
    -0.06
     takeover
    -0.06
     DRV
    -0.06
     BEGIN
    -0.06
    лен
    -0.06
     summit
    -0.06
     potrze
    -0.06
     workbook
    -0.06
     PROFITS
    -0.06
    .kafka
    -0.06
    POSITIVE LOGITS
    pper
    0.07
    rible
    0.07
     Nic
    0.07
    .general
    0.06
    ใบ
    0.06
    译
    0.06
    .payload
    0.06
    पन
    0.06
    .op
    0.06
     NJ
    0.06
    Activations Density 0.029%

    No Known Activations