© 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. 93495
    Prev
    Next
    INDEX
    Explanations

    versus

    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
    );}
    -0.08
     آمده
    -0.07
     Buffer
    -0.06
     ذ
    -0.06
     WA
    -0.06
    虚
    -0.06
     мощ
    -0.06
     Gareth
    -0.06
     داشت
    -0.06
     Kenya
    -0.06
    POSITIVE LOGITS
    edido
    0.07
    BI
    0.07
     pleasantly
    0.07
    ":"/
    0.06
    bro
    0.06
    ged
    0.06
    -carousel
    0.06
     outraged
    0.06
    Correct
    0.06
    �
    0.06
    Activations Density 0.000%

    No Known Activations