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. 54441
    Prev
    Next
    INDEX
    Explanations

    claiming as your own

    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
     підвищ
    -0.06
    협
    -0.06
     sıkıntı
    -0.06
    瑞
    -0.06
    寫
    -0.06
     поруш
    -0.06
     ValidationError
    -0.06
    gx
    -0.06
     혹
    -0.06
     이동
    -0.05
    POSITIVE LOGITS
     recognizing
    0.07
    FUL
    0.07
     quits
    0.07
     framing
    0.06
     tits
    0.06
    ουμε
    0.06
    .Touch
    0.06
    ERRUPT
    0.06
     voxel
    0.06
    IFY
    0.06
    Activations Density 0.006%

    No Known Activations