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. 53884
    Prev
    Next
    INDEX
    Explanations

    Mixed content snippets

    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
    .GetDirectoryName
    -0.06
    nam
    -0.06
     Rue
    -0.06
    .called
    -0.06
    شة
    -0.06
    _configure
    -0.06
     RNG
    -0.06
    rz
    -0.06
    .TimeUnit
    -0.06
     NES
    -0.06
    POSITIVE LOGITS
    Italian
    0.07
     github
    0.06
     Github
    0.06
     ут
    0.06
     outr
    0.06
     partitions
    0.06
     ){↵
    0.06
     Anthony
    0.06
    yclerview
    0.06
    (pg
    0.06
    Activations Density 0.000%

    No Known Activations