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. 15-RESID-POST-AA
    6. 54135
    Prev
    Next
    INDEX
    Explanations

    Complete sentences

    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
     ф
    -0.07
     赤
    -0.07
    unicip
    -0.06
     सम
    -0.06
     Struct
    -0.06
    ुरस
    -0.06
     tooltip
    -0.06
     alt
    -0.05
     notices
    -0.05
     рас
    -0.05
    POSITIVE LOGITS
    ")));↵
    0.07
    Adresse
    0.07
     hern
    0.07
    _ios
    0.07
     }]
    0.07
    мерикан
    0.06
    Contr
    0.06
    Prior
    0.06
     GetLastError
    0.06
    997
    0.06
    Activations Density 0.063%

    No Known Activations