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. 11-RESID-POST-AA
    6. 50538
    Prev
    Next
    INDEX
    Explanations

    diversity

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kron
    -0.08
    133
    -0.08
    IBILITY
    -0.07
    GEST
    -0.07
    存
    -0.07
     connectivity
    -0.07
    ları
    -0.07
     summoned
    -0.06
     adjoining
    -0.06
     ı
    -0.06
    POSITIVE LOGITS
    θρώ
    0.07
    (nullptr
    0.06
     hrd
    0.06
    tiğini
    0.06
    .major
    0.06
    (Sender
    0.06
    玻璃
    0.06
    iện
    0.06
     serviceName
    0.05
     whipping
    0.05
    Activations Density 0.033%

    No Known Activations