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. 123070
    Prev
    Next
    INDEX
    Explanations

    javascript code

    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
     Но
    -0.07
    Exc
    -0.07
     тиж
    -0.07
     pObj
    -0.07
     kond
    -0.07
     lượt
    -0.07
    -hook
    -0.06
     Aut
    -0.06
     représ
    -0.06
     palavra
    -0.06
    POSITIVE LOGITS
    اتی
    0.07
    -non
    0.07
    lab
    0.06
     Agency
    0.06
    .event
    0.06
     fictional
    0.06
    IBLE
    0.06
    wise
    0.06
    ného
    0.06
    ignty
    0.06
    Activations Density 0.001%

    No Known Activations