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. 11-RESID-POST-AA
    6. 104433
    Prev
    Next
    INDEX
    Explanations

    up

    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
    пример
    -0.07
     predic
    -0.07
    would
    -0.07
     incom
    -0.07
    were
    -0.06
     dessa
    -0.06
     couleur
    -0.06
    риф
    -0.06
     dieser
    -0.06
    snake
    -0.06
    POSITIVE LOGITS
     out
    0.10
     up
    0.09
     Out
    0.09
     Up
    0.09
     back
    0.09
    -Out
    0.08
     DOWN
    0.08
     Down
    0.08
    ่ต
    0.08
     leftover
    0.07
    Activations Density 0.179%

    No Known Activations