© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 73315
    Prev
    Next
    INDEX
    Explanations

    something is too late

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ิทยาศาสตร
    -0.07
    Jam
    -0.07
     Reduced
    -0.07
     Flavor
    -0.07
     サ
    -0.07
     Yog
    -0.06
    guards
    -0.06
    Attached
    -0.06
     Pok
    -0.06
     존재
    -0.06
    POSITIVE LOGITS
     DID
    0.07
     svaz
    0.06
     갤로그로
    0.06
    cerpt
    0.06
     अलग
    0.06
     diagn
    0.06
     Deck
    0.06
    registry
    0.06
    VEST
    0.06
     ligne
    0.05
    Activations Density 0.064%

    No Known Activations