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. 104205
    Prev
    Next
    INDEX
    Explanations

    Millennial generation

    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
    婦
    -0.07
     MEP
    -0.06
     masses
    -0.06
     Patients
    -0.06
    Nuevo
    -0.06
     eligible
    -0.06
     spikes
    -0.06
     lapse
    -0.06
    Good
    -0.06
    Are
    -0.06
    POSITIVE LOGITS
    ffic
    0.06
    خاص
    0.06
    [iVar
    0.06
    OMUX
    0.06
    ๆ
    0.06
     παιδ
    0.06
    .Fprintf
    0.06
    setAttribute
    0.06
     stalk
    0.06
     الات
    0.06
    Activations Density 0.015%

    No Known Activations