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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 20304
    Prev
    Next
    INDEX
    Explanations

    $

    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
    5
    -0.07
     vertex
    -0.07
     Na
    -0.07
    enderit
    -0.07
    3
    -0.07
     Books
    -0.06
    .Member
    -0.06
     Vertex
    -0.06
    _means
    -0.06
     antivirus
    -0.06
    POSITIVE LOGITS
     $
    0.07
    ोज
    0.06
    lete
    0.06
    735
    0.06
    .lua
    0.06
    ……
    0.06
     £
    0.06
     даль
    0.06
     Melissa
    0.06
    лося
    0.05
    Activations Density 0.036%

    No Known Activations