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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 53736
    Prev
    Next
    INDEX
    Explanations

    Arguments and analysis

    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
     pointed
    -0.07
    805
    -0.07
     valore
    -0.06
    卢
    -0.06
     รอง
    -0.06
     Elementary
    -0.06
     besch
    -0.06
     telah
    -0.06
     ตาม
    -0.06
    deki
    -0.06
    POSITIVE LOGITS
    _LL
    0.06
     cyt
    0.06
    cript
    0.06
     userProfile
    0.06
     electron
    0.06
     컨
    0.06
    =name
    0.06
    =\"/
    0.06
    рош
    0.06
     KT
    0.06
    Activations Density 0.076%

    No Known Activations