Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 7-RESID-POST-AA
    6. 31335
    Prev
    Next
    INDEX
    Explanations

    treatments

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .TH
    -0.07
    _analysis
    -0.06
     corners
    -0.06
     Ri
    -0.06
    Hu
    -0.06
     trading
    -0.06
    щини
    -0.06
    .words
    -0.06
     impression
    -0.06
    hasil
    -0.06
    POSITIVE LOGITS
     manoe
    0.06
    .ribbon
    0.06
    ภาคม
    0.06
     العربية
    0.06
     forwarded
    0.06
     thaimassage
    0.06
     drž
    0.06
     melod
    0.06
    IsActive
    0.06
    北市
    0.06
    Activations Density 0.031%

    No Known Activations