© 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. 10811
    Prev
    Next
    INDEX
    Explanations

    recommend

    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
     falls
    -0.07
     contrary
    -0.06
    linewidth
    -0.06
     live
    -0.06
    ollision
    -0.06
     bevor
    -0.06
    orderBy
    -0.06
    	continue
    -0.06
    �
    -0.06
    par
    -0.06
    POSITIVE LOGITS
    Enumerable
    0.07
    óa
    0.06
    URY
    0.06
     maintenant
    0.06
     mũi
    0.06
    .setAuto
    0.06
    RATE
    0.06
     thức
    0.06
    �
    0.06
     Pie
    0.06
    Activations Density 0.036%

    No Known Activations