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. 11-RESID-POST-AA
    6. 81075
    Prev
    Next
    INDEX
    Explanations

    ed

    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
     rebels
    -0.07
     olanak
    -0.07
     kotlinx
    -0.07
     promoting
    -0.07
     navCtrl
    -0.06
    'a
    -0.06
    -прав
    -0.06
     Filip
    -0.06
     promoted
    -0.06
     goTo
    -0.06
    POSITIVE LOGITS
     axle
    0.06
    (Game
    0.06
     conject
    0.06
    めた
    0.06
     목록
    0.06
     overdose
    0.06
    _SID
    0.06
    後の
    0.06
    冊
    0.06
    ILT
    0.06
    Activations Density 0.002%

    No Known Activations