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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 31761
    Prev
    Next
    INDEX
    Explanations

    before

    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
    ManagedObject
    -0.07
    رض
    -0.06
    .Controls
    -0.06
    佐
    -0.06
    irim
    -0.06
     Nin
    -0.06
    {Name
    -0.06
     قر
    -0.06
     tekrar
    -0.06
    MMdd
    -0.06
    POSITIVE LOGITS
     USE
    0.07
     computers
    0.07
     Computers
    0.06
     carpet
    0.06
     bozuk
    0.06
     ресур
    0.06
    shows
    0.06
     books
    0.06
     мот
    0.06
    \L
    0.06
    Activations Density 0.000%

    No Known Activations