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. 61322
    Prev
    Next
    INDEX
    Explanations

    DW

    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
     nach
    -0.07
     Boyd
    -0.06
    Thanks
    -0.06
    vard
    -0.06
     size
    -0.06
    trim
    -0.06
    306
    -0.06
     behaved
    -0.06
    D
    -0.06
     taxi
    -0.06
    POSITIVE LOGITS
    ↵
    0.06
    =model
    0.06
    단체
    0.06
    editar
    0.06
     adorn
    0.06
    dal
    0.06
     �
    0.06
    .AddSingleton
    0.06
    ="",
    0.06
    회의
    0.06
    Activations Density 0.105%

    No Known Activations