© 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. 27520
    Prev
    Next
    INDEX
    Explanations

    directly

    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
     �
    -0.06
     permitted
    -0.06
     Wagner
    -0.06
     Kristen
    -0.06
     Wow
    -0.06
     skipping
    -0.06
     schl
    -0.06
     Campbell
    -0.06
     Pruitt
    -0.06
     tuyệt
    -0.06
    POSITIVE LOGITS
     direct
    0.16
     directly
    0.15
     Direct
    0.13
    Direct
    0.11
     DirectX
    0.09
     직접
    0.08
    direct
    0.08
    기에
    0.08
    react
    0.08
     přím
    0.08
    Activations Density 0.025%

    No Known Activations