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. 11-RESID-POST-AA
    6. 100343
    Prev
    Next
    INDEX
    Explanations

    comma

    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
     frais
    -0.06
     Huffman
    -0.06
     slik
    -0.06
    Fed
    -0.06
     Shepard
    -0.06
    ishlist
    -0.06
    Pause
    -0.06
    амет
    -0.05
    代表
    -0.05
     Phase
    -0.05
    POSITIVE LOGITS
     меся
    0.08
    ย
    0.07
     reign
    0.07
     generally
    0.07
     poder
    0.07
     Bl
    0.06
    建
    0.06
     감
    0.06
    /m
    0.06
     integ
    0.06
    Activations Density 0.003%

    No Known Activations