© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 56109
    Prev
    Next
    INDEX
    Explanations

    ise

    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
    =$((
    -0.06
    ंधन
    -0.06
    ũ
    -0.06
     Manila
    -0.06
     Reduce
    -0.06
     DataSet
    -0.06
    .DataBind
    -0.06
    jon
    -0.06
    illa
    -0.06
     ف
    -0.06
    POSITIVE LOGITS
     numerous
    0.07
    Immediate
    0.07
    oji
    0.07
    idis
    0.07
    islation
    0.06
    ीर
    0.06
    UTDOWN
    0.06
     ORIGINAL
    0.06
    ountain
    0.06
    -binding
    0.06
    Activations Density 0.014%

    No Known Activations