© 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. 93341
    Prev
    Next
    INDEX
    Explanations

    Saying

    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
     hled
    -0.07
     starred
    -0.07
     empez
    -0.07
     方法
    -0.06
     Graz
    -0.06
     submodule
    -0.06
    DUCT
    -0.06
     kHz
    -0.06
    GLOSS
    -0.06
     Pinterest
    -0.06
    POSITIVE LOGITS
     Corrections
    0.06
     alacak
    0.06
    -da
    0.06
     suppose
    0.06
    -ignore
    0.06
    ログ
    0.06
    olik
    0.06
     indebted
    0.06
    rades
    0.06
    bib
    0.06
    Activations Density 0.004%

    No Known Activations