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. 110806
    Prev
    Next
    INDEX
    Explanations

    everyday

    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
    ?>><?
    -0.07
     şer
    -0.06
     Portal
    -0.06
    /gif
    -0.06
    ёт
    -0.06
     جغراف
    -0.06
    guest
    -0.06
     supporter
    -0.06
    chl
    -0.06
     Δεν
    -0.06
    POSITIVE LOGITS
    _right
    0.07
    	change
    0.06
    say
    0.06
     beneficial
    0.06
    �
    0.06
    ovic
    0.06
    iệc
    0.06
    웨디시
    0.06
    _status
    0.06
    من
    0.06
    Activations Density 0.000%

    No Known Activations