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. 11-RESID-POST-AA
    6. 104452
    Prev
    Next
    INDEX
    Explanations

    License headers

    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
    -group
    -0.07
    'є
    -0.07
     Poster
    -0.06
    _)↵
    -0.06
    次
    -0.06
     reach
    -0.06
     Edu
    -0.06
     dok
    -0.06
    ены
    -0.06
     Mir
    -0.06
    POSITIVE LOGITS
    urnal
    0.07
     akıl
    0.07
    èles
    0.06
    σωπ
    0.06
     processor
    0.06
    ियम
    0.06
    _shutdown
    0.06
    =logging
    0.06
     ли
    0.06
    aret
    0.06
    Activations Density 0.001%

    No Known Activations