Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 127497
    Prev
    Next
    INDEX
    Explanations

    materials and polymers

    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
     era
    -0.07
    nge
    -0.06
     sunt
    -0.06
    [curr
    -0.06
    erase
    -0.06
     Країна
    -0.06
     noe
    -0.06
    ocaust
    -0.06
     genocide
    -0.06
     син
    -0.06
    POSITIVE LOGITS
     đột
    0.07
    ば
    0.06
     conseils
    0.06
    trajectory
    0.06
    ireccion
    0.06
     threats
    0.06
    χεία
    0.06
     sausage
    0.06
     brochure
    0.06
     CSL
    0.06
    Activations Density 0.078%

    No Known Activations