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. 80805
    Prev
    Next
    INDEX
    Explanations

    Storytelling

    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
     amps
    -0.07
    名
    -0.07
    							
    ↵
    -0.07
     supremacy
    -0.06
     stroj
    -0.06
     Jazz
    -0.06
    Υ
    -0.06
    웠
    -0.06
    に対
    -0.06
    ือ
    -0.06
    POSITIVE LOGITS
    _DEPRECATED
    0.08
    AntiForgeryToken
    0.07
    зна
    0.06
    filesystem
    0.06
    /x
    0.06
    CancelButton
    0.06
     LETTER
    0.06
     AppRoutingModule
    0.06
    _INITIALIZER
    0.06
     [{"
    0.06
    Activations Density 0.104%

    No Known Activations