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. 15-RESID-POST-AA
    6. 31768
    Prev
    Next
    INDEX
    Explanations

    Code and syntax elements

    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
    इस
    -0.07
    LLU
    -0.06
     اوت
    -0.06
    .getId
    -0.06
     elimin
    -0.06
     ride
    -0.06
     `<
    -0.06
     прев
    -0.06
     alter
    -0.06
    Dept
    -0.06
    POSITIVE LOGITS
     введ
    0.07
     supernatural
    0.06
     Passive
    0.06
    /cmd
    0.06
    orarily
    0.06
    нии
    0.06
    #ifndef
    0.06
     enrolled
    0.06
    !("{}",
    0.06
    (크기
    0.06
    Activations Density 0.010%

    No Known Activations