© 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. 90753
    Prev
    Next
    INDEX
    Explanations

    Informal text snippets

    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
     Begins
    -0.07
    .Cl
    -0.07
     внутрен
    -0.07
    upro
    -0.07
     tieten
    -0.06
    WB
    -0.06
    اصيل
    -0.06
     другой
    -0.06
    (Exception
    -0.06
     )"
    -0.06
    POSITIVE LOGITS
     Mes
    0.07
     contro
    0.06
     conferred
    0.06
    жди
    0.06
    icí
    0.06
    orio
    0.06
    amanho
    0.06
    Behavior
    0.06
     фер
    0.06
    	debug
    0.05
    Activations Density 0.047%

    No Known Activations