© 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. 11-RESID-POST-AA
    11. 53023
    Prev
    Next
    INDEX
    Explanations

    non-English languages

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     About
    -0.07
    ,application
    -0.07
     obstacle
    -0.07
     Determines
    -0.06
     Bout
    -0.06
    	It
    -0.06
     Isn
    -0.06
     parasite
    -0.06
     ey
    -0.06
     Perf
    -0.06
    POSITIVE LOGITS
     quiere
    0.09
     quiero
    0.09
     wollte
    0.08
     quer
    0.07
     wollen
    0.07
     Wanna
    0.07
     wanna
    0.07
     willen
    0.07
     хочу
    0.07
     chce
    0.07
    Activations Density 0.028%

    No Known Activations