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. 25211
    Prev
    Next
    INDEX
    Explanations

    businesses

    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
    adores
    -0.06
    علق
    -0.06
    该
    -0.06
    correct
    -0.06
     Tories
    -0.06
     shout
    -0.06
     indexing
    -0.06
    essage
    -0.06
    不了
    -0.06
     rowspan
    -0.06
    POSITIVE LOGITS
    posium
    0.07
    fontWeight
    0.07
    Tap
    0.06
    ImplOptions
    0.06
    bitmap
    0.06
     dubbed
    0.06
    eson
    0.06
      
    0.06
     announc
    0.06
     dispose
    0.06
    Activations Density 0.039%

    No Known Activations