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. 19-RESID-POST-AA
    6. 83214
    Prev
    Next
    INDEX
    Explanations

    [@

    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
    Au
    -0.07
     흐
    -0.07
     tém
    -0.07
    Theo
    -0.07
     收
    -0.07
     disdain
    -0.07
     dc
    -0.07
     -------
    -0.07
    経
    -0.07
     Going
    -0.06
    POSITIVE LOGITS
     Πλη
    0.06
     APC
    0.06
     Anadolu
    0.06
    riends
    0.06
     asoci
    0.06
    LOC
    0.06
    rowser
    0.06
    .Sequential
    0.06
    bách
    0.06
    ivals
    0.05
    Activations Density 0.008%

    No Known Activations