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. 21787
    Prev
    Next
    INDEX
    Explanations

    to

    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
    "L
    -0.06
    nowrap
    -0.06
    분
    -0.06
    料
    -0.06
    traits
    -0.06
    _patient
    -0.06
     اه
    -0.06
    (include
    -0.06
     Spiel
    -0.06
     algo
    -0.06
    POSITIVE LOGITS
    _interrupt
    0.06
     sacked
    0.06
     رفع
    0.06
     sucking
    0.06
    $wp
    0.06
    Cannot
    0.06
    ildi
    0.06
     budouc
    0.06
    	scanf
    0.06
     qw
    0.06
    Activations Density 0.001%

    No Known Activations