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. 19-RESID-POST-AA
    6. 44882
    Prev
    Next
    INDEX
    Explanations

    varieties and options

    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
     آزاد
    -0.06
     KeyEvent
    -0.06
    organizations
    -0.06
     Hope
    -0.06
    IntervalSince
    -0.06
    friends
    -0.06
     bans
    -0.06
     reduced
    -0.06
    :block
    -0.06
     Cách
    -0.06
    POSITIVE LOGITS
     Imaging
    0.07
     Para
    0.07
    zung
    0.06
     ζω
    0.06
    IDES
    0.06
    ۲۹
    0.06
    ủa
    0.06
     деся
    0.06
     McCart
    0.06
     tamp
    0.06
    Activations Density 0.056%

    No Known Activations