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. 27-RESID-POST-AA
    6. 73196
    Prev
    Next
    INDEX
    Explanations

    scientific measurements

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     NavParams
    -0.06
    idar
    -0.06
    -mouth
    -0.06
    Invoice
    -0.06
     classrooms
    -0.06
    -seat
    -0.06
    -layer
    -0.06
    ική
    -0.06
    Customer
    -0.06
     hart
    -0.06
    POSITIVE LOGITS
     mourning
    0.07
    ;display
    0.07
    .jp
    0.07
    10
    0.06
     مشکل
    0.06
     Spiele
    0.06
     전에
    0.06
    .ob
    0.06
     ศ
    0.06
     Alicia
    0.06
    Activations Density 0.010%

    No Known Activations