Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 23-RESID-POST-AA
    6. 104779
    Prev
    Next
    INDEX
    Explanations

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    协
    -0.07
     вперед
    -0.07
    (scroll
    -0.06
     getLast
    -0.06
    继续
    -0.06
    	CHECK
    -0.06
    Either
    -0.06
     Nhĩ
    -0.06
    )?;↵
    -0.06
     `<
    -0.06
    POSITIVE LOGITS
     않았
    0.06
    	Context
    0.06
    าการ
    0.06
    /red
    0.06
     ist
    0.06
     milestones
    0.06
    Para
    0.06
     gather
    0.06
    ╝
    0.06
    /rem
    0.05
    Activations Density 0.103%

    No Known Activations