© 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. 9434
    Prev
    Next
    INDEX
    Explanations

    Cloud computing and Git

    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
    优
    -0.07
     angles
    -0.06
    ’yi
    -0.06
    بيرة
    -0.06
    +y
    -0.06
    ятся
    -0.06
    amy
    -0.06
     Kara
    -0.06
     warp
    -0.06
     Ρ
    -0.06
    POSITIVE LOGITS
     sensational
    0.07
    .Results
    0.07
     अभ
    0.07
    )frame
    0.07
    (QWidget
    0.06
     départ
    0.06
    (strtolower
    0.06
     Yugosl
    0.06
    _daily
    0.06
     getSource
    0.06
    Activations Density 0.056%

    No Known Activations