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. 14578
    Prev
    Next
    INDEX
    Explanations

    guessing, suspicion

    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
    .ImageView
    -0.07
    رق
    -0.07
     رسم
    -0.06
     Caribbean
    -0.06
     سیم
    -0.06
     Israelis
    -0.06
    .Parser
    -0.06
    联盟
    -0.06
    ायत
    -0.06
    σιμο
    -0.06
    POSITIVE LOGITS
     posible
    0.06
    _Check
    0.06
     monde
    0.06
     volley
    0.06
    airro
    0.06
    净
    0.06
    width
    0.06
    xic
    0.06
    ICON
    0.06
    asured
    0.06
    Activations Density 0.033%

    No Known Activations