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. 122972
    Prev
    Next
    INDEX
    Explanations

    Code or technical text

    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
    унк
    -0.06
    ival
    -0.06
    vari
    -0.06
     CPC
    -0.06
     evolves
    -0.06
    ап
    -0.06
    xz
    -0.06
     bookmark
    -0.06
    roadcast
    -0.06
    zek
    -0.06
    POSITIVE LOGITS
     neglig
    0.07
    :none
    0.06
     kaynağı
    0.06
     постро
    0.06
     nerves
    0.06
    	LEFT
    0.06
    黄
    0.06
     تصویر
    0.06
     Buffered
    0.06
     creditors
    0.06
    Activations Density 0.000%

    No Known Activations