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. 104396
    Prev
    Next
    INDEX
    Explanations

    plans and processes

    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
     hakkı
    -0.06
    .hostname
    -0.06
    )':
    -0.06
     záb
    -0.06
    CLASS
    -0.06
    Normals
    -0.06
    (Socket
    -0.06
     особливо
    -0.06
    744
    -0.06
    "description
    -0.06
    POSITIVE LOGITS
     Verd
    0.08
    kinson
    0.07
    �回
    0.06
    旁
    0.06
    іти
    0.06
     UA
    0.06
     meas
    0.06
     kus
    0.06
     東
    0.06
     belt
    0.06
    Activations Density 0.054%

    No Known Activations