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. 104428
    Prev
    Next
    INDEX
    Explanations

    notice

    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
    riteria
    -0.07
    ,omitempty
    -0.06
    ,W
    -0.06
     findet
    -0.06
     camino
    -0.06
    ик
    -0.06
     перей
    -0.06
    ']:
    -0.06
     erfahren
    -0.06
     بعضی
    -0.06
    POSITIVE LOGITS
    admins
    0.07
    .water
    0.07
     carbs
    0.07
    cbd
    0.07
    azaar
    0.07
    987
    0.06
    /Instruction
    0.06
    će
    0.06
    eward
    0.06
    .Local
    0.06
    Activations Density 0.016%

    No Known Activations