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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 53776
    Prev
    Next
    INDEX
    Explanations

    retroviruses

    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
    상위
    -0.07
    '";
    ↵
    -0.07
     landscaping
    -0.06
    awns
    -0.06
    แก
    -0.06
     menor
    -0.06
     Д
    -0.06
     tête
    -0.06
     MIX
    -0.06
     합니다
    -0.06
    POSITIVE LOGITS
     performance
    0.07
    rix
    0.07
    \v
    0.07
    昨
    0.07
     mast
    0.07
    (cid
    0.06
    ¸
    0.06
    	module
    0.06
    _campaign
    0.06
    arti
    0.06
    Activations Density 0.007%

    No Known Activations