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. 79788
    Prev
    Next
    INDEX
    Explanations

    .'

    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
    lightbox
    -0.06
    igger
    -0.06
    lander
    -0.06
    writer
    -0.06
    mony
    -0.06
    animals
    -0.06
    ελ
    -0.06
    860
    -0.06
     HIT
    -0.06
    adas
    -0.06
    POSITIVE LOGITS
     zeigt
    0.07
    .↵↵↵↵↵
    0.06
     vm
    0.06
     miêu
    0.06
     vám
    0.06
     Visibility
    0.06
     nehmen
    0.06
    #↵
    0.06
     نیروی
    0.06
     اگر
    0.06
    Activations Density 0.004%

    No Known Activations