© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 72737
    Prev
    Next
    INDEX
    Explanations

    sadly

    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
     calculate
    -0.08
    итет
    -0.07
    ivatel
    -0.07
    allon
    -0.06
     '('
    -0.06
    toi
    -0.06
     flights
    -0.06
     Calculate
    -0.06
    Violation
    -0.06
     warmer
    -0.06
    POSITIVE LOGITS
     ordained
    0.07
     Unfortunately
    0.06
     особенно
    0.06
    %%↵
    0.06
    cpt
    0.06
     pains
    0.06
     honest
    0.06
    ㅠ
    0.06
    ↵↵↵↵↵↵
    0.06
     longtime
    0.06
    Activations Density 0.008%

    No Known Activations