Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 21847
    Prev
    Next
    INDEX
    Explanations

    isions

    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
     정부
    -0.06
     cracking
    -0.06
    (desc
    -0.06
     Multiply
    -0.06
    Feel
    -0.06
     Instantiate
    -0.06
    (pro
    -0.06
     clearing
    -0.06
    Tween
    -0.06
    (msg
    -0.06
    POSITIVE LOGITS
    /doc
    0.06
     tyranny
    0.06
    678
    0.06
    />↵↵
    0.06
    ↵↵    ↵
    0.06
    raises
    0.06
    --;↵
    0.06
    ALSE
    0.06
    itty
    0.06
    łu
    0.06
    Activations Density 0.001%

    No Known Activations