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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 15-RESID-POST-AA
    6. 53883
    Prev
    Next
    INDEX
    Explanations

    good

    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
    _strcmp
    -0.07
     Director
    -0.07
     đứng
    -0.07
     discrepan
    -0.07
    /routes
    -0.06
    .area
    -0.06
     cavern
    -0.06
    uelles
    -0.06
    _BEFORE
    -0.06
    _selected
    -0.06
    POSITIVE LOGITS
    fib
    0.06
    eward
    0.06
    essed
    0.06
    šem
    0.06
    puted
    0.06
    gb
    0.06
    Orange
    0.06
    ियर
    0.06
    adget
    0.05
    lene
    0.05
    Activations Density 0.011%

    No Known Activations