© 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. 103535
    Prev
    Next
    INDEX
    Explanations

    fraud

    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
    ğa
    -0.07
     pans
    -0.07
    	begin
    -0.07
     Begin
    -0.06
    社
    -0.06
    ارت
    -0.06
     Riv
    -0.06
    	background
    -0.06
    tube
    -0.06
    ازل
    -0.06
    POSITIVE LOGITS
     річ
    0.07
    ={{↵
    0.06
     że
    0.06
     darüber
    0.06
     εκ
    0.06
    fst
    0.06
     září
    0.06
     пропози
    0.06
    profit
    0.06
    ::$
    0.06
    Activations Density 0.076%

    No Known Activations