© 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. 19-RESID-POST-AA
    6. 57765
    Prev
    Next
    INDEX
    Explanations

    code

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    散
    -0.07
    ,//
    -0.06
    股份有限公司
    -0.06
     redhead
    -0.06
    751
    -0.06
     ApiResponse
    -0.06
     HomeComponent
    -0.06
     بیشتری
    -0.06
    .Phone
    -0.06
     ↵↵
    -0.06
    POSITIVE LOGITS
     )))
    0.07
     toi
    0.06
     latina
    0.06
    ACIÓN
    0.06
    )])↵
    0.06
     persist
    0.06
     yı
    0.06
    =>
    0.06
     extents
    0.06
    ologi
    0.06
    Activations Density 0.130%

    No Known Activations