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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 15-RESID-POST-AA
    6. 21282
    Prev
    Next
    INDEX
    Explanations

    which

    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
    yer
    -0.07
     traveller
    -0.07
     Polo
    -0.06
    baru
    -0.06
    FE
    -0.06
    779
    -0.06
     neuron
    -0.06
    pla
    -0.06
    =@"
    -0.06
    reward
    -0.06
    POSITIVE LOGITS
     which
    0.07
     آنچه
    0.07
    ість
    0.07
     которым
    0.06
     Combat
    0.06
    跳
    0.06
    ��
    0.06
     degli
    0.06
    オン
    0.06
    punkt
    0.06
    Activations Density 0.032%

    No Known Activations