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. 15-RESID-POST-AA
    6. 111000
    Prev
    Next
    INDEX
    Explanations

    originally

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     roast
    -0.07
    (one
    -0.07
     Sussex
    -0.06
    Merc
    -0.06
    Pl
    -0.06
    	Ext
    -0.06
     std
    -0.06
     mqtt
    -0.06
     facts
    -0.06
     wi
    -0.06
    POSITIVE LOGITS
     originally
    0.08
     Originally
    0.07
     podob
    0.07
     hatten
    0.07
    phants
    0.07
     initially
    0.07
    ughter
    0.07
    laughs
    0.07
    すべて
    0.07
     há
    0.07
    Activations Density 0.011%

    No Known Activations