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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 15-RESID-POST-AA
    6. 128248
    Prev
    Next
    INDEX
    Explanations

    View Controller

    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
    UITextField
    -0.06
    ’↵↵
    -0.06
    energy
    -0.06
    361
    -0.06
     psy
    -0.06
    (register
    -0.06
    memcpy
    -0.06
     mệ
    -0.05
    +A
    -0.05
    солют
    -0.05
    POSITIVE LOGITS
     involves
    0.07
    source
    0.07
    <TSource
    0.07
    ViewController
    0.07
    (auto
    0.07
    [ix
    0.07
     Kat
    0.07
     preventing
    0.07
     quick
    0.07
     whichever
    0.07
    Activations Density 0.004%

    No Known Activations