© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 115034
    Prev
    Next
    INDEX
    Explanations

    timeframes/restrictions

    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
     student
    -0.07
    license
    -0.07
    bz
    -0.06
     exposes
    -0.06
     vulnerabilities
    -0.06
     overload
    -0.06
     hiển
    -0.06
    allocator
    -0.06
    _qos
    -0.06
     berg
    -0.06
    POSITIVE LOGITS
    .lucene
    0.06
     остав
    0.06
    创新
    0.06
    лаб
    0.06
    λί
    0.06
     마음
    0.06
    gli
    0.06
    �
    0.06
    롭
    0.06
     Replies
    0.06
    Activations Density 0.091%

    No Known Activations