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. 15-RESID-POST-AA
    6. 73904
    Prev
    Next
    INDEX
    Explanations

    then

    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
    5
    -0.07
     سی
    -0.07
    marginTop
    -0.07
    nama
    -0.06
    OT
    -0.06
    EE
    -0.06
    559
    -0.06
    package
    -0.06
    :</
    -0.06
     homicides
    -0.06
    POSITIVE LOGITS
     frameborder
    0.07
     Parade
    0.06
     extraordinary
    0.06
    eline
    0.06
    (priv
    0.06
    bose
    0.06
    uibModal
    0.06
    诊
    0.06
     вона
    0.06
    __":↵
    0.06
    Activations Density 0.020%

    No Known Activations