© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 52318
    Prev
    Next
    INDEX
    Explanations

    delicate

    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
     προς
    -0.07
     усп
    -0.07
     astonished
    -0.07
    影響
    -0.07
    syn
    -0.07
     saints
    -0.07
    782
    -0.06
     velocity
    -0.06
     plain
    -0.06
    .currentUser
    -0.06
    POSITIVE LOGITS
     delicate
    0.14
     fragile
    0.10
     delic
    0.08
     frail
    0.07
    ali
    0.07
    手
    0.07
     HOLDERS
    0.06
    _Handle
    0.06
    .Axis
    0.06
    リカ
    0.06
    Activations Density 0.007%

    No Known Activations