© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 120830
    Prev
    Next
    INDEX
    Explanations

    website

    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
    *.
    -0.07
    berger
    -0.07
    imeters
    -0.06
    Virtual
    -0.06
    illage
    -0.06
     African
    -0.06
    Giving
    -0.06
    AIR
    -0.06
    .nextSibling
    -0.06
    igators
    -0.06
    POSITIVE LOGITS
     cush
    0.06
    iasi
    0.06
     blessed
    0.06
     amort
    0.06
    (klass
    0.06
    мот
    0.06
    лося
    0.06
     наслід
    0.06
    ESS
    0.06
     adher
    0.06
    Activations Density 0.795%

    No Known Activations