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. 11-RESID-POST-AA
    6. 66086
    Prev
    Next
    INDEX
    Explanations

    texture

    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
    -part
    -0.06
    される
    -0.06
     prec
    -0.06
     Builds
    -0.06
    nik
    -0.06
    _Server
    -0.06
    signal
    -0.06
    \base
    -0.06
    sockets
    -0.06
     روی
    -0.06
    POSITIVE LOGITS
    ции
    0.07
    hom
    0.06
    ического
    0.06
    ัพท
    0.06
     ALTER
    0.06
    veled
    0.06
    rimp
    0.06
    óg
    0.06
    ecessarily
    0.06
    iesz
    0.06
    Activations Density 0.000%

    No Known Activations