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

    Neuronpedia

    APICircuit 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. 11-RESID-POST-AA
    6. 104360
    Prev
    Next
    INDEX
    Explanations

    programming help requests

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ались
    -0.08
    asuring
    -0.06
    .pe
    -0.06
    .Face
    -0.06
    лись
    -0.06
     sung
    -0.06
    WG
    -0.06
    modity
    -0.06
    ются
    -0.06
    .ParseException
    -0.06
    POSITIVE LOGITS
    (hostname
    0.06
    	File
    0.06
    teri
    0.06
    .sin
    0.06
     responsive
    0.06
     DirectX
    0.06
     pObj
    0.06
    ('*
    0.06
    .Mobile
    0.06
    bbox
    0.06
    Activations Density 0.061%

    No Known Activations