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. 81082
    Prev
    Next
    INDEX
    Explanations

    trap

    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
     isso
    -0.07
    _UNIX
    -0.07
     packet
    -0.06
     Bible
    -0.06
    .callback
    -0.06
     فشار
    -0.06
    abella
    -0.06
    UIBarButtonItem
    -0.06
     Gavin
    -0.06
    .realpath
    -0.06
    POSITIVE LOGITS
    	↵↵↵
    0.06
    /read
    0.06
     ensure
    0.06
    .sem
    0.06
    uč
    0.06
     ra
    0.06
    .Background
    0.06
    appropri
    0.06
     }↵↵↵↵↵↵
    0.06
    	create
    0.06
    Activations Density 0.011%

    No Known Activations