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. 111426
    Prev
    Next
    INDEX
    Explanations

    /twitter

    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
     ensured
    -0.07
    ονται
    -0.07
     ayuda
    -0.07
     assertEquals
    -0.07
    ウィ
    -0.06
    .Bind
    -0.06
    .have
    -0.06
    _com
    -0.06
     Yuk
    -0.06
     Vương
    -0.06
    POSITIVE LOGITS
    WithPath
    0.07
    tout
    0.06
     Ger
    0.06
     wikipedia
    0.06
     forIndexPath
    0.06
    ilis
    0.06
    _ix
    0.06
    §
    0.06
    turn
    0.06
    salt
    0.06
    Activations Density 0.000%

    No Known Activations