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. 103879
    Prev
    Next
    INDEX
    Explanations

    Code and programming

    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
     repeating
    -0.08
    луж
    -0.07
     outset
    -0.07
     LV
    -0.07
    Psy
    -0.07
    urrencies
    -0.06
    参
    -0.06
     ther
    -0.06
     exempt
    -0.06
    arım
    -0.06
    POSITIVE LOGITS
    -initialized
    0.07
    важ
    0.06
    akistan
    0.06
     alertDialog
    0.06
    iminal
    0.06
    addClass
    0.06
     став
    0.06
    "),↵↵
    0.06
     GOP
    0.06
    ,status
    0.06
    Activations Density 0.034%

    No Known Activations